The index · everything in the almanac
Search
Look up a team, a repository, a gathering or a paper, by keyword or by meaning.
No matches for “”
The index · everything in the almanac
Look up a team, a repository, a gathering or a paper, by keyword or by meaning.
No matches for “”
No matches for “”
Layer
Open sourcekeyword match
OpenClaw Foundation/openclaw · TypeScript
OpenClaw (born as Clawdbot in late 2025) is a self-hosted personal agent that connects your chats, email, browser and terminal into one always-on assistant. Its explosive growth — hundreds of thousands of stars within months — made 'personal agent harness' a mainstream category.
Open sourcekeyword match
Anthropic (community)/modelcontextprotocol · TypeScript
MCP standardizes how applications provide context and tools to LLMs — servers expose tools, resources and prompts over a JSON-RPC protocol. Adopted by OpenAI, Google, Microsoft and effectively the whole ecosystem, it is the connective tissue of modern harnesses.
Open sourcekeyword match
Prefect/fastmcp · Python
FastMCP (created by Jeremiah Lowin, now stewarded by Prefect) became the de-facto standard for authoring MCP servers in Python — decorators, auth, proxying and deployment in a few lines. Now among the most-starred tools in the protocol layer.
Open sourcekeyword match
Browser Use/browser-use · Python
Browser Use is an open-source Python library for browser agents. Version 1.0 (November 2026) replaced the 0.x DOM-extraction agent: the model now writes Python cells in one persistent REPL that calls browser-harness helpers and the Chrome DevTools Protocol directly. It runs on any LLM, locally or on Browser Use Cloud, and also ships a CLI and MCP server.
Startupkeyword match
The integration layer: hundreds of managed tools your agents can call. · San Francisco, CA
Composio handles auth, schemas, observability and reliability for the external SaaS tools an agent uses — 'plumbing for agentic actions' across Slack, GitHub, Salesforce and 250+ other surfaces.
Startupkeyword match
A registry and toolchain for MCP servers.
Smithery indexes and helps deploy MCP (Model Context Protocol) servers — a distribution layer for the tool ecosystem agents connect to.
Startupkeyword match
Search API purpose-built for AI agents. · San Francisco, CA
Exa (formerly Metaphor) provides neural search and web-crawl APIs tuned for agent consumption — live, cited knowledge for agents instead of stale training data.
Startupkeyword match
Search and extraction API optimized for LLMs and agents.
Tavily gives agents a single API for search, crawling and in-depth extraction, returning clean, cited results — a common tool in research-agent harnesses.
Startupkeyword match
A natural-language IDE for building agents. · London, UK
Wordware (YC) lets domain experts and engineers co-build agents in a document-like natural-language programming environment — 'Notion for prompt-to-agent development'.
Startupkeyword match
Type-safe Python infrastructure — now including agents.
Pydantic builds the data-validation library underlying most of the Python AI ecosystem, plus Logfire (observability) and Pydantic AI (typed agent framework) — the type-safety layer of the harness.
Startupkeyword match
The gateway between your harness and every model provider. · United States
BerriAI builds LiteLLM — the open-source proxy that normalizes 100+ LLM providers behind the OpenAI API with routing, budgets and observability. A quiet standard inside production agent stacks.
Startupkeyword match
Headless browser infrastructure built for AI agents. · United States
Browserbase runs fleets of headless browsers as an API — sessions, proxies, stealth, debugging — so agents can act on the web without operators managing browser infrastructure. Also builds the Stagehand SDK.
Startupkeyword match
The company behind the open-source web-agent library. · United States
Browser Use maintains the eponymous 100k-star open-source library for vision-capable browser agents and commercializes it for enterprises automating web workflows.
Startupkeyword match
Human approval and context engineering for agents. · United States
HumanLayer builds tooling for human-in-the-loop agent workflows and authored '12-Factor Agents' — the widely-cited methodology for building production harnesses. Now focused on agentic code review tooling.
Startupkeyword match
Authorization and tool infrastructure for AI agents. · San Francisco, CA
Arcade (arcade.dev) builds the identity and authorization layer for agents — OAuth-backed tool execution, credential management and fine-grained access control so agents can act on a user's behalf without inheriting god-mode credentials. Raised a $60M Series A in 2026.
Startupkeyword match
The sessionless, relentless 24/7 personal agent.
Comma is an always-on personal agent with no session boundaries — 'no full stop until it's done'. Its distributed harness, Salix, loads tiny eBPF programs into the cluster to watch events around the clock and wake the main agent loop only when something needs it.
Startupkeyword match
Build, deploy and publish agent apps as MCPs.
Recurse makes it easy to build an agent app, deploy it, and publish it as an MCP server usable from Claude, Codex or any MCP client — hosting handled, started from your coding agent via a SKILL.md. A bridge between harness skills and deployable agent infrastructure.
Startupkeyword match
The browser API for AI agents. · San Francisco, CA
Steel Dev provides a batteries-included open-source browser (steel-browser) plus a cloud Browser API for agents and apps — isolated Chrome sessions, stealth, residential proxies, CAPTCHA handling and persistent profiles. The open-source core in the hosted browser-infrastructure lane.
Startupkeyword match
Open drivers, cross-OS sandboxes and benchmarks for computer-use agents. · San Francisco, CA
Cua (YC Spring 2025) builds infrastructure for computer-use agents. Cua Spaces is a desktop app that gives agents full desktops: macOS VMs built locally, or Linux images, on the user's own machines or cloud. Cua Driver lets agents inspect and operate native apps and browsers on macOS, Windows and Linux through a CLI, MCP or typed SDKs. The stack also includes Lume (macOS VMs), the Cua SDK and CLI for local sandboxes, CUA-S1 small models for computer-use decisions, and Cua Bench for simulated tasks. The repo is MIT-licensed, while the Spaces app is source-available under FSL-1.1-MIT.
Startupkeyword match
Open-source Ghostty-based macOS terminal for running many AI coding agents at once, by Manaflow. · San Francisco, CA
cmux is a native macOS terminal, built in Swift and AppKit on libghostty, for multitasking across AI coding agents. It is made by Manaflow (YC Summer 2024), which its YC profile calls an open-source applied AI lab building next-gen devtools. Features include notification rings and a panel that flag panes needing agent attention, and vertical tabs showing git branch, PR status, ports and the latest notification. It also has a scriptable in-app browser, SSH workspaces, a one-command Claude Code teammate mode, and a CLI and socket API for automation. The terminal is GPL-3.0-or-later, and parts of the server code are BUSL-1.1.
Startupkeyword match
Computer-use agents: the open-source Agent S framework, the Sai agent and the Simular API. · San Francisco, CA
Simular, founded by former DeepMind scientists, builds computer-use agents that operate desktop and web apps by looking at the screen and clicking, typing and scrolling. Its open-source Agent S framework runs on macOS, Windows and Linux; the project reports Agent S3 as the first to surpass human performance on OSWorld (72.60%) and released Agent S4 in October 2026. Commercially it offers Sai, a production computer-use agent, and the Simular API for giving agents autonomous cloud computers. In December 2025 it announced a $21.5M Series A led by Felicis, with NVentures and South Park Commons participating.
Startupkeyword match
Fullstack MCP framework and cloud for MCP apps and servers.
Manufact is the company behind mcp-use, an open-source (MIT) TypeScript framework for building, testing and shipping MCP servers, MCP Apps for ChatGPT and Claude connectors. The framework offers Zod-typed tools, React 'Views' bound to tools, a built-in Inspector and an agent-first, headless CLI for scaffolding, invoking and deploying servers. Manufact's site positions it as 'the cloud for production MCP', helping teams get onto ChatGPT and Claude plugin stores, see how agents use their servers and test releases across clients and harnesses.
Startupkeyword match
Bifrost: open-source LLM, MCP and agent gateway.
Maxim AI builds Bifrost, an open-source (Apache-2.0) AI gateway written in Go that acts as an LLM gateway, MCP gateway and agent gateway. It exposes one OpenAI-compatible API across providers including OpenAI, Anthropic, AWS Bedrock, Google Vertex, Azure, Mistral, Groq and Ollama, with automatic failover, load balancing, semantic caching, virtual keys, budgets and an MCP 'Code Mode'. The project claims under 200 microseconds of overhead at 5k RPS. Enterprise deployments add clustering, guardrails, adaptive load balancing and private networking.
Startupkeyword match
TrueForge: open-source agent harness runtime layer.
TrueFoundry, which sells an enterprise AI gateway and MCP gateway, maintains TrueForge, an open-source (MIT) agent harness that runs the agent execution loop: model calls, MCP tools (with header auth or OAuth), git-backed SKILL.md skills, sandboxed code execution (Daytona today), tool approvals, context management and session state. TrueForge exposes this through a chat UI, an HTTP API with a TypeScript SDK and an embeddable UI SDK, and adds context engineering such as subagents, deferred tool loading, Code Mode and compaction. It runs locally (SQLite) or hosted (Postgres + Redis).
Startupkeyword match
Agent enablement platform and registry for building, evaluating and distributing agent skills. · London, UK
Tessl, founded by Guy Podjarny, describes itself as the management layer between developers and their coding agents (Claude Code, Cursor, GitHub Copilot, Gemini and others). The Tessl Platform acts as a control plane for agent context, tackling duplicate skills, tracking skill quality and usage with before-and-after evals, and scanning skills for security. The Tessl Registry indexes skills across an organisation, and Loops run skills on a schedule for tasks like code review and docs maintenance. In September 2025 it launched the Tessl Framework and Spec Registry for spec-driven development.
Startupkeyword match
A Git forge for agent-human collaboration that versions the reasoning behind code.
Entire, led by former GitHub CEO Thomas Dohmke, is a Git-compatible forge that stores the reasoning behind changes alongside code. Its open-source CLI (first released as Checkpoints) captures agent sessions such as prompts, tools used and token use, initially from Claude Code and Gemini CLI. The forge adds 'Trails' as a pull-request replacement with agent reviews and evals, code-graph plus session memory for agent context, agentic search across code, commits and sessions, and secret redaction. It raised a $60M seed led by Felicis in February 2026.
Startupkeyword match
Fast specialized models for coding agents: apply, search, compaction and routing. · Columbus, OH
Morph (YC S23) provides a model API for coding agents. Fast Apply models merge LLM-generated edits into files (the site cites 10,500 tok/s), WarpGrep is a code-search subagent, and Compact compresses context while keeping original bytes; it also serves open-weight agent-loop models and a router. Access is via an OpenAI-compatible API, TypeScript and Python SDKs, OpenRouter, an MCP server, and CLI/skills for Claude Code, Cursor, Codex and OpenCode, with self-hosting for enterprise. YC lists founder Tejas Bhakta and Columbus, OH.
Startupkeyword match
Messaging between coding agents: every agent gets an address, across people, vendors and tools.
clawalkietalkie gives each coding agent an address, such as cc: for Claude Code, cx: for Codex, cu: for Cursor, gm: for Gemini CLI and gh: for GitHub Actions, so agents can hand work to each other, including a teammate's agent at a team address, and report what they are working on to one status board. CI can message the agent that can fix a failing build and wait for the reply. Claude Code's mod starts a turn when a message arrives; other agents read their inbox through an MCP server. The clients are open source (MIT) and talk to a hosted relay.
Startupkeyword match
The coding agent for open models · San Francisco, CA
Command Code is a terminal coding agent (`npm i -g command-code`) built for open-weight models such as DeepSeek, Kimi, GLM, Qwen and MiniMax. It also supports Anthropic, OpenAI, Google and xAI models. Its harness validates and repairs tool calls as they happen and targets high cache-hit rates. 'Taste' learns from accepts, rejects and edits and turns them into shareable project skills. It offers headless mode, a background sandbox, a desktop app, custom agents and MCP servers.
Startupkeyword match
The deterministic engine for agents to make estate-wide code changes.
Moderne offers agent tools, including Trigrep and Prethink, and a CLI that can direct GitHub Copilot to run changes, such as a Java 25 upgrade, across a set of repositories. Each agent-driven 'factory' runs a recipe and observes its effect across every repository in the set. Build or test failures in one repository feed back to refine the recipe, so it can make the change safely in repositories with weaker test coverage.
Startupkeyword match
Codebase-aware model router for coding agents
Bito's Governor is a router that grounds each coding-agent request in your codebase and sends it to a right-sized model. It combines a code context engine with a complexity-scoring model router. It works with Claude Code, Cursor, Codex and GitHub Copilot through a base-URL change, and supports per-key budgets. Bito also offers a system-aware AI PR review agent.
Startupkeyword match
Knowledge platform for teams and agents · San Francisco, CA
Dosu captures what people and agents learn and keeps that knowledge shared and current, so agents use fewer tokens and make fewer mistakes. It syncs with GitHub, GitLab, Slack, Notion and Confluence and stores knowledge as portable markdown. Coding agents connect through the Dosu MCP Server.
Startupkeyword match
The context layer for your entire codebase
Sourcegraph provides code search and code-graph context for developers and AI coding agents, including an MCP server for 'code graph knowledge for agents' and Deep Search with citation-backed answers. Agentic Batch Changes is described as an agent for code changes at scale. The company cites its own CodeScaleBench report for improvements in agent speed and token use.
Startupkeyword match
AI coding agent that thinks, plans, then builds
CodeGPT is an AI coding agent for VS Code and JetBrains IDEs. It reads the codebase, proposes an editable plan and writes code with step-by-step approval, can run terminal commands with approval, and connects to APIs, docs and databases via MCP. Users can bring their own keys for Claude, GPT, Gemini, Grok or local models via Ollama and LM Studio.
Startupkeyword match
Cloud browsers, sandboxes and web data APIs for AI agents
Hyperbrowser hosts cloud Chrome sessions that can be controlled with Playwright or Puppeteer, with persistent logins and live inspection. It also offers isolated sandboxes with snapshots and a web API for fetching, crawling and search that returns Markdown, HTML, screenshots or JSON matching a schema. Agent tasks can be run with HyperAgent, Browser Use or computer-use models, and the service ships Node.js and Python SDKs, a CLI and MCP.
Startupkeyword match
Cloud-hosted browser infrastructure for computer-use and browser agents
Anchor describes itself as a cloud-hosted browser that lets AI agents use the web the way a person would. Features include Anchor Chromium (a stealth Chromium fork), OmniConnect for login handling, a built-in VPN and a Web Action Cache that turns planned tasks into deterministic code. It can be deployed in the customer's own cloud and is reachable through an SDK or MCP.
Startupkeyword match
Browser infrastructure for web agents and automations
Kernel provides isolated cloud Chromium sessions controlled through an API, SDK or CLI, using Playwright, CDP, WebDriver BiDi or computer use. It supports persistent profiles, managed auth that keeps credentials and MFA codes out of the agent conversation, and stealth mode with captcha solving and proxies. It also has live view, session replay, a hosted MCP server, and browser pools for latency-sensitive work.
Startupkeyword match
Managed headless browsers for automation and AI agents, over MCP, Puppeteer or Playwright
Browserless runs headless browsers in the cloud that Puppeteer, Playwright and Selenium connect to over WebSocket. It offers an MCP server with scraping, crawling, search and export tools, BrowserQL (a GraphQL interface with stealth options), and REST endpoints for screenshots, PDFs and scraping. It lists integrations with Browser Use, Stagehand, LangChain and Claude Code.
Startupkeyword match
Browser platform and framework for AI web agents
Notte provides cloud browser sessions with anti-detection, residential proxies and CAPTCHA solving, plus browser agents that navigate sites from natural-language tasks. It can deploy browser automations as serverless functions with cron scheduling, and offers personas and secret vaults so credentials stay away from the LLM. It has an MCP server, a CLI and an agent skill for coding agents. The site says it is backed by Y Combinator (W25).
Startupkeyword match
Web infrastructure for AI to search, extract, monitor and reason over the world's information
Parallel offers Search, Extract, Task (deep research), FindAll (entity datasets), Monitor and Responses APIs, built on its own Parallel Web Index. Outputs can include citations, reasoning traces and calibrated confidence scores through its Basis framework. It ships Python and TypeScript SDKs and a Parallel Search MCP server, and works with LangChain and the Vercel AI SDK.
Startupkeyword match
AWS platform for building, connecting and running production AI agents with any framework or model
Amazon Bedrock AgentCore is AWS's platform for building, connecting and running production AI agents with any framework or model. It includes a harness for deploying agents and a Gateway that handles authentication and access control for tool calls to MCP servers, APIs and Lambda functions. It also has observability and evaluation tools for tracing agent behavior and testing variations against real traffic.
Startupkeyword match
Access. Identity. Checkout. The Agent Trust Stack.
Skyfire gives agents verified identity and payment credentials that work across the open internet. It offers a Know Your Agent (KYA) credential and an agentic wallet for card and stablecoin payments with recorded user approvals.
Startupkeyword match
How AI Agents Use Money
Catena is a banking and governance platform for AI agents. It supports payments, treasury and other services.
Startupkeyword match
Make Your Website Actionable For Agents
nekuda makes websites actionable for agents using WebMCP. Sites can build full tools with a coding agent or start from a scan of the site, and get full visibility into agent activity.
Startupkeyword match
Email Inbox API for AI Agents
AgentMail is email infrastructure built for AI agents. Agents get their own inboxes and can send, receive and act on email at scale.
Startupkeyword match
Open-source AI governance platform and MCP gateway
Obot's GitHub repo describes it as a 'Complete AI Governance Platform from Obot AI'. The open-source project is written in Go under the MIT license and is actively maintained.
Startupkeyword match
Open-source MCP and skills gateway
Metorial gives an organization one MCP URL behind its SSO, with 1,000+ integrations, role-based tool access, audit logs and shared skills in Claude, ChatGPT and Cursor. Its GitHub repo describes it as connecting any AI model to 1200+ integrations via MCP, CLI or API.
Startupkeyword match
Enterprise MCP gateway and AI control plane
Lunar.dev offers an enterprise MCP gateway, an AI gateway and agent governance to secure and govern AI applications and agents. Its open-source repo describes an agent-native MCP gateway for governance and security. The site says Boomi has completed its acquisition of Lunar.dev.
Startupkeyword match
MCP server registry, inspector and gateway
Glama runs an MCP server registry that it describes as a superset of the official MCP Registry, with every server scanned, scored and testable in the browser. The site lists 112,011 MCP servers, 38,854 connectors and over 1.1M tools indexed.
Startupkeyword match
MCP gateway for security, deployment and observability
MCP Manager by Usercentrics is an MCP gateway for AI governance. It provides guardrails, RBAC, logging and visibility for companies in regulated industries. Features include an MCP registry, logs and observability, and PII filtering.
Startupkeyword match
Hosted MCP connecting AI clients to 9,000+ apps
Zapier MCP connects Claude, ChatGPT, Cursor or any AI client to 9,000+ apps. The agent finds the right action and runs it, with auth and permissions managed by Zapier. The GitHub repo is the official plugin distribution for the hosted Zapier MCP server.
Startupkeyword match
Connect your product and AI agents to 1,000+ APIs
Nango is integration infrastructure for connecting products and AI agents to 1,000+ APIs. It is used to build, run and maintain integrations in code. The open-source repo is written in TypeScript.
Startupkeyword match
Build and govern MCP servers on company context
Credal is an enterprise platform where teams build and govern MCP servers, with curated context, scoped tools, enforced instructions and parameters, and cost-to-accuracy evals per workflow. It also offers an Agent Builder and an Agent Registry.
Startupkeyword match
Security gateway for AI agents with purpose-based authorization
Clawvisor is a security gateway that sits between agents and services like email, calendar and code. It checks each request against the human-approved task, injects credentials server-side so agents never see them, and logs every action. It is source-available, self-hostable or managed, and backed by Y Combinator.
Startupkeyword match
MCP integration platform and live environments for AI agents
Klavis AI's open-source platform provides MCP integrations so agents can use tools reliably at scale. The company also builds live environments and training data for agents, including Dockerized long-horizon coding tasks and tool-use data across 600+ tools and SaaS apps. It is backed by Y Combinator.
Startupkeyword match
A context layer for coding agents that indexes code and documentation for Cursor, Claude Code and MCP clients.
Nia indexes codebases and documentation and serves that context to coding agents such as Cursor and Claude Code, and to other MCP clients, so agents answer from the real source rather than guesses. The Y Combinator S25 company launched on Hacker News in December 2025 with 131 points.
Startupkeyword match
Searches past sessions across coding agents, so skills and memories are not locked into one provider.
Skillsync started from a lock-in complaint: "We get locked into a single provider and their agent as we invest in skills and memories over time." It launched in September 2026 to make sessions portable across coding agents, and its site now leads with fast search over past sessions across agents ("search so fast it feels like memory"). Y Combinator W26.
Startupkeyword match
The fastest persistent computer for agents; launched as "Vercel for Agents" connecting any LLM to any MCP tool.
Dedalus Labs launched on Hacker News in August 2025 as "Vercel for Agents", an SDK that connects any LLM to any MCP tool. Its site now positions the company as the "Fastest Persistent Computer for Agents", offering persistent VMs for agent workloads. Y Combinator S25.
Startupkeyword match
An AI on-call agent that drops read-only probes into production to debug live systems.
HyperProbe launched on Hacker News in August 2026 with a way for Cursor and Claude to place read-only probes in production and debug live systems. Its site now leads with an "AI on-call agent" built on the same idea. Y Combinator S26.
Startupkeyword match
Free iPhone companion for Claude Code and Codex sessions on your own Mac and Linux computers.
CodeConnect brings sessions from multiple paired Mac and Linux computers into one iPhone view. Both Claude Code and Codex support approval requests and messages. Claude Code also supports questions, diff review, hunk comments and a live terminal. Codex keeps its native approval choices and supports stopping a turn, without a phone terminal. Tailscale is the default connection; session content travels directly between the phone and computers. A separate push relay handles notification metadata, not session content. The daemon is MIT-licensed; iOS source is available under separate personal-build terms. The iPhone app is free and requires iOS 17 or later.
Startupkeyword match
The self-hosted governance layer between your AI agents and your business systems, on your rules. · Darmstadt
Self-hosted MCP gateway for small and mid-sized companies, delivered as one Docker container. Credentials stay in a built-in vault, permissions are deny-by-default per token and team, every tool call is written to an audit log, and personal data can be pseudonymised deterministically before it reaches the model. Connectors cover REST, upstream MCP, SQL and files, including German ERP and accounting systems. Open core: connector specs, plugins, recipes and deploy files are Apache 2.0.
Open sourcekeyword match
Pydantic/pydantic-ai · Python
Pydantic AI brings the type-safety and validation of Pydantic to agents — typed tools, structured outputs, dependency injection and graph-based control flow, from the team behind the most-used data validation library in Python.
Open sourcekeyword match
HarnessRouter/harnessrouter · TypeScript
HarnessRouter Community Edition is a self-hosted, Apache-2.0 unified interface for agent harnesses: run Codex, Claude Code, Hermes, Pi, DeepSeek Harness and more through one API with sessions, streaming, files, cancellation and failure handling. Implements the Unified Harness Protocol (UHP), an open standard — your keys, your infrastructure.
Open sourcekeyword match
AG-UI / CopilotKit/ag-ui · TypeScript
AG-UI standardizes the event stream between agent backends and application frontends — generative UI, tool states, human-in-the-loop — so any agent runtime can drive any web app.
Open sourcekeyword match
Composio/composio · Python
Composio provides 250+ managed, authenticated integrations (GitHub, Slack, CRMs, browsers…) exposed as agent tools, with observability and access control — 'auth + integrations as a service' for the harness layer.
Open sourcekeyword match
Browserbase/stagehand · TypeScript
Stagehand (by Browserbase) adds AI-driven act()/extract()/observe() primitives on top of Playwright — the pragmatic middle ground between brittle selectors and fully autonomous browsing.
Open sourcekeyword match
Skyvern AI/skyvern · Python
Skyvern drives browsers with a combination of LLM reasoning and vision — automating workflows on sites without APIs, with workflow-building tools on top.
Open sourcekeyword match
BerriAI/litellm · Python
LiteLLM normalizes 100+ providers behind the OpenAI API format with a proxy server for routing, budgets, rate limits and observability. A quiet but essential piece of most production harnesses.
Open sourcekeyword match
Google/gemini-cli · TypeScript
Gemini CLI is an Apache-2.0 terminal agent with file, shell and web tools, MCP servers and extensions. Since June 18, 2026, free and Google AI Pro/Ultra access has moved to Antigravity CLI; Gemini CLI is now maintained for Gemini Code Assist Standard/Enterprise and Code Assist for GitHub, and is not tuned for Gemini 4 models.
Open sourcekeyword match
goose (Block-initiated)/goose · Rust
goose is a Rust-based general-purpose agent with a desktop app for macOS, Linux and Windows, a CLI and an API. It works with 15+ model providers and connects to MCP extensions; built at Block, it is now part of the Agentic AI Foundation at the Linux Foundation.
Open sourcekeyword match
Cline/cline · TypeScript
Cline pioneered the autonomous VS Code agent — plan/act modes, MCP tool use, checkpoints — and now ships as an SDK and CLI too. One of the most-used open coding agents.
Open sourcekeyword match
Jesse Vincent (obra)/superpowers · MDX
Superpowers is a software development method for coding agents, built from composable skills that trigger on their own. The agent first asks what you want to build and why, shows the design in short sections, writes an implementation plan built on red/green TDD, then runs subagent-driven development to carry out and review each task. It installs as a plugin for Claude Code, Codex, Cursor, Gemini CLI, Copilot CLI, Antigravity, OpenCode, Pi, Hermes and other harnesses.
Open sourcekeyword match
Anthropic/skills · Python
Anthropic's official Agent Skills: SKILL.md-based folders (instructions, scripts, resources) that Claude dynamically loads in Claude Code, Claude.ai and the API. The reference implementation for progressive-disclosure skill packs.
Open sourcekeyword match
Open Interpreter/openinterpreter · Python
Open Interpreter lets language models run code on your computer — a code-execution harness where the model writes code and the harness executes it with confirmation gates. Oriented to open models (DeepSeek, Kimi, Qwen), it made 'the agent is the loop' tangible early.
Open sourcekeyword match
Upstash/context7 · TypeScript
Context7 is an MCP server that injects up-to-date, version-specific library docs into an agent's context on demand — killing the stale-training-data hallucinations that plague codegen. One of the most-installed tool layers in modern harnesses.
Open sourcekeyword match
Garry Tan/gstack · TypeScript
GStack is Garry Tan's MIT-licensed set of Markdown slash-command skills (about 50, including /office-hours, /review, /qa, /ship, /autoplan and /retro) that give a coding agent specialist roles such as CEO, eng manager, designer, QA lead, security officer and release engineer. Claude Code is fully supported; setup can also install it for Codex, OpenCode, Cursor, Factory Droid, Kiro, Copilot CLI, Antigravity, Gemini CLI, OpenClaw and Hermes as experimental hosts.
Open sourcekeyword match
Addy Osmani/agent-skills · MDX
Addy Osmani's production-grade skill pack: 24 engineering skills and 4 specialist agent personas encoding senior-dev workflows (spec through deploy) across 70+ coding agents including Claude Code, Cursor and Copilot.
Open sourcekeyword match
Vercel/ai · TypeScript
The Vercel AI SDK is the React/Node toolkit for streaming, tool calls and agent-style UIs, provider-agnostic across every major model API. For TypeScript harness builders it is often the layer between the loop and the model.
Open sourcekeyword match
Google/agents-cli · TypeScript
Google's Agents CLI turns any coding assistant into an expert at creating, evaluating and deploying agents — layering official skills on top of the harness you already run instead of shipping another agent loop. The harness as config, from Google.
Open sourcekeyword match
Steel/steel-browser · TypeScript
Steel Browser is the open-source core of Steel's Browser API: cloud or self-hosted Chrome sessions with stealth, residential proxies, CAPTCHA solving and persistent profiles — the only open-source offering in the hosted browser-infrastructure lane.
Open sourcekeyword match
Cheaper Inference/OmniRoute · TypeScript
OmniRoute is an MIT-licensed, local-first AI gateway. It exposes one OpenAI-compatible endpoint at localhost:20128/v1 and routes across hundreds of providers: the README says 375, the site 352. Fallback is quota-aware. It offers 19 routing strategies, circuit breakers and model lockouts, semantic caching, and a context-compression pipeline that it claims saves 15-95% of tokens. It also has a built-in MCP server and A2A server. It works with Claude Code, Codex, Cursor, OpenCode, Cline and Copilot. The project has joined Cheaper Inference, which offers a hosted version.
Open sourcekeyword match
router-for-me/CLIProxyAPI · Go
CLIProxyAPI is an MIT-licensed Go proxy server. It exposes OpenAI-, Gemini-, Claude-, Codex- and Grok-compatible API endpoints backed by CLI agent accounts, with OAuth login for OpenAI Codex, Claude Code and Grok Build. It supports streaming and WebSocket responses, function calling, multimodal input, and round-robin load balancing across multiple accounts per provider. It can also use OpenAI-compatible upstreams such as OpenRouter. A reusable Go SDK lets other tools embed the proxy, and EasyCLIProxyAPI is a separate desktop client for it.
Open sourcekeyword match
farion1231/cc-switch · Rust
CC Switch is an MIT-licensed Tauri 2 desktop app for Windows, macOS and Linux. It manages configuration for sixteen agent tools: Claude Code, Claude Desktop, Codex, Gemini CLI, Grok Build, OpenCode, OpenClaw, Hermes Agent, Pi, MiniMax Code, Antigravity CLI, Kimi Code, Oh My Pi, DeepSeek Harness, GitHub Copilot CLI and Tencent WorkBuddy. It switches API providers in one click from 90+ presets and changes only the endpoint, key and model. MCP servers and skills are managed centrally and synced to selected tools. A local routing mode does format conversion and failover, with an optional filter that replaces personal data and keys before requests are forwarded, and the app also shows session logs and tracks usage and quota.
Open sourcekeyword match
DeusData/codebase-memory-mcp · C
codebase-memory-mcp is an MIT-licensed MCP server, written in C, that indexes code, documentation, configuration and infrastructure into a persistent local knowledge graph. Its 17 MCP tools combine symbol, text and semantic search with callers, dependencies and file outlines, and Hybrid LSP adds type resolution. It traces relationships through Docker, Kubernetes, Terraform and CI config, and supports change impact and test selection. The installer configures dozens of agent clients and adds skills and context hooks. An optional visual companion, CBM Lens, is in beta. Analysis runs locally.
Open sourcekeyword match
AstrBotDevs/AstrBot · Python
AstrBot is an open-source, all-in-one agent chatbot platform that plugs LLM agents into mainstream instant-messaging apps, including QQ, WeChat Work, Feishu, DingTalk, Telegram and Slack. It supports agents, MCP, skills, knowledge bases, personas and automatic context compression. It can also integrate agent platforms such as Dify, Alibaba Cloud Bailian and Coze. It ships an agent sandbox for isolated code and shell execution, a WebUI and web ChatUI, and a plugin system with more than 1,000 one-click plugins. Its GitHub description calls it an OpenClaw alternative.
Open sourcekeyword match
Seth Hobson/agents · Python
wshobson/agents is a single collection of plugins, agents, skills and commands that installs across Claude Code, OpenAI Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot and Pi. The README defines a harness as the coding tool that loads and runs the components. The catalog lists 94 plugins, and the local source holds 202 agents, 185 skills and 105 commands. Every component comes from a shared Markdown source, and installation is adapted to each harness: native marketplaces for Claude Code, Codex and Cursor, and generated artifacts for the others. A capability matrix documents model mappings, tool permissions and hooks for each harness.
Open sourcekeyword match
ByteDance/UI-TARS-desktop · TypeScript
TARS is ByteDance's open-source multimodal AI agent stack, and the repository ships two projects. Agent TARS is a general multimodal agent that brings GUI-agent and vision abilities to the terminal, computer, browser and product. It runs through a CLI and a Web UI and connects to real-world MCP tools. UI-TARS Desktop is a desktop app that provides a native GUI agent based on the UI-TARS model. It ships local and remote computer operators as well as browser operators.
Open sourcekeyword match
Vercel Labs/skills · TypeScript
skills is Vercel Labs' command-line tool for the open agent-skills ecosystem. Agent skills are reusable instructions that teach coding agents how to perform tasks. The tool installs, finds, lists, checks, updates and removes skills, and scaffolds new ones (npx skills add / find / update / init). It installs to the current project or globally and lets users choose which coding agents to target. The README lists OpenCode, Claude Code, Codex, Cursor and 75 more supported agents. Skills can also be used without installing, and skills.sh serves as the discovery directory.
Open sourcekeyword match
AgentScope/QwenPaw · TypeScript
QwenPaw is a personal AI assistant from the AgentScope organisation that runs locally or in the cloud and is reachable from DingTalk, Lark, WeChat, Discord, Telegram, iMessage and QQ. It has three-layer memory powered by ReMe and a built-in local runtime with QwenPaw-Flash models (2B to 35B-A3B), plus Ollama, LM Studio and 14+ cloud providers. Security features include a kernel-level sandbox, Tool Guard, File Guard, a skill scanner and access policies. It also supports sub-agents, Agent Communication Protocol (ACP) orchestration, skills, plugins and MCP. Recent releases added browser-use, computer-use and Codex/Qoder agent integration.
Open sourcekeyword match
Mert Koseoglu/context-mode · TypeScript
Context Mode is an MCP server for AI coding agents that targets context-window bloat. Its sandbox tools keep raw tool output out of context; the README cites 315 KB reduced to 5.4 KB. It tracks file edits, git operations, tasks, errors and decisions in SQLite. After compaction it retrieves only the relevant events through FTS5/BM25 search. It also has the model write scripts that print only results (ctx_execute) instead of reading many files. It covers 17 platforms: hook-capable ones such as Claude Code get automatic routing enforcement, and the rest use a routing file. It is licensed under the Elastic License 2.0.
Open sourcekeyword match
rtk-ai/rtk · Rust
RTK is an agent-agnostic token-optimisation proxy shipped as a single Rust binary with no dependencies. It intercepts shell commands and compresses their output before the agent reads it. It supports 100+ commands with under 10 ms of overhead, and its GitHub description claims a 60-90% cut in token use on common dev commands. Examples include tree-format ls, signature-first file reads, grouped grep matches, compact git status, diff and log, and failures-only output for cargo, npm, pytest and go test. The README notes that savings apply to bash output only and are estimated as bytes/4, not a full-bill reduction.
Open sourcekeyword match
Oraios AI/serena · Python
Serena is an MCP toolkit that gives coding agents semantic code retrieval, editing, refactoring and debugging tools similar to an IDE's. The tools work at the symbol level and use the code's relational structure instead of line numbers or plain text search. It integrates with any MCP client or LLM. Serena v2 added a REPL-based, code-execution agent interface. The project publishes agent-written evaluations from Claude Code and Codex CLI runs on large codebases. Licensing is per component: the SolidLSP language-server layer is MIT and the Serena application is GPL-3.0-or-later.
Open sourcekeyword match
NVIDIA/SkillSpector · Python
SkillSpector scans AI agent skills (for Claude Code, Codex CLI, Gemini CLI and MCP) before installation. It accepts Git repos, URLs, zips, directories or single files and checks 71 vulnerability patterns across 17 categories, including prompt injection, data exfiltration, privilege escalation, supply chain, memory poisoning and tool misuse. Analysis combines fast static checks with optional LLM semantic evaluation, live OSV.dev CVE lookups, a 0-100 risk score and terminal, JSON, Markdown or SARIF output. It is part of NVIDIA's Verified Skills pipeline that scans and signs skills before publication.
Open sourcekeyword match
Browser Use/browser-harness · Python
Browser Harness, from Browser Use, gives coding agents control of the user's real Chrome browser (open pages, click, type, read, download) while logged in as the user. It connects over the Chrome DevTools Protocol and is set up by pasting one prompt into Claude Code or Codex; a SKILL.md teaches the workflow and the agent writes missing helpers into its own workspace. An MCP server (`browser-harness-mcp`) exposes the helpers to any MCP client. In Browser Use's own BU Bench V2.1 comparison it had no statistically significant score difference versus Playwright MCP or Chrome DevTools MCP but the lowest median token use.
Open sourcekeyword match
lsdefine/GenericAgent · Python
GenericAgent is a minimal autonomous agent framework: about 3K lines of seed code, 9 atomic tools and a ~100-line agent loop that give an LLM system-level control of a local computer, covering browser, terminal, filesystem and keyboard/mouse. Its design principle is to evolve rather than preload skills: each solved task is crystallized into a reusable skill, building a personal skill tree over time, and the project claims about 6x lower token consumption. The README states official channels are GitHub and gaagent.ai, with DintalClaw as the sole authorized commercial partner. MIT licensed.
Open sourcekeyword match
Zilliz/claude-context · TypeScript
Claude Context is an MCP plugin from Zilliz that adds semantic code search to Claude Code and other coding agents. It indexes a codebase into a vector database (Zilliz Cloud / Milvus) using an embedding model such as OpenAI's, then retrieves only the relevant code into the agent's context instead of loading whole directories, which the project says keeps costs manageable on large codebases. Configuration examples cover Claude Code, OpenAI Codex CLI and other MCP clients; requires Node.js 20+.
Open sourcekeyword match
iFlytek/skillhub · Java
SkillHub is iFlytek's open-source, self-hosted platform that gives teams a private, governed place to share agent skills. Teams publish skill packages with semantic versioning and tags such as beta and stable, push them into namespaces, and let others find them via search or install them through a CLI. Governance features include RBAC and audit logs, and it deploys on-premise behind a firewall with Docker Compose or Kubernetes. It also offers versioned skill suites and a REST API.
Open sourcekeyword match
HolmesGPT (CNCF)/holmesgpt · Python
HolmesGPT is an open-source AI agent that investigates production incidents and finds root causes. Robusta.Dev created it, and CNCF accepted it as a Sandbox project on October 8, 2025. It runs an agentic loop over live observability data through built-in toolsets for Prometheus, Grafana, Datadog, Kubernetes and others, plus custom REST API toolsets, with server-side filtering and per-tool memory limits to keep large payloads out of context. An operator mode runs scheduled health checks in the background, and it can pull alerts from AlertManager, PagerDuty or Jira and write findings back.
Open sourcekeyword match
NetEase Youdao/LobsterAI · TypeScript
LobsterAI is an MIT-licensed desktop agent from NetEase Youdao, built on OpenClaw. Given a plain-language task, it reads local files, runs tools and scripts, drives a browser and edits Word, Excel and PowerPoint documents, asking before sensitive actions. It supports role-based kits, skills and MCP connectors, scheduled recurring tasks, and remote control of the desktop agent from WeChat, Feishu, DingTalk and Telegram. Sessions are stored locally; users can use built-in models or bring their own keys.
Open sourcekeyword match
Matt Pocock (AI Hero)/skills · Shell
Matt Pocock's skills repository collects the agent skills he uses daily, designed to be small, adaptable and model-agnostic as an alternative to process-owning frameworks. Skills include /grill-with-docs (builds a glossary and ADRs), /to-spec, /to-tickets, /implement, /tdd (red-green-refactor), /diagnosing-bugs, /improve-codebase-architecture, /triage and /retro. They install as plugins for Claude Code, Codex and GitHub Copilot, or via skills.sh as editable files.
Open sourcekeyword match
GitHub/spec-kit · Python
Spec Kit is GitHub's open-source toolkit that gives AI coding agents structured processes, reusable templates and documented outcomes. Its core process is spec-driven development, run through commands such as /speckit-constitution, /speckit-specify, /speckit-plan, /speckit-tasks and /speckit-implement; bundled extensions add bug fixing and idea assessment. The Specify CLI initialises a project for a chosen agent integration (GitHub Copilot by default, with others supported), and primitives let teams adapt or build their own processes.
Open sourcekeyword match
Vercel Labs/agent-browser · Rust
agent-browser is a Vercel Labs browser-automation CLI built for AI agents, implemented as a native Rust binary. It downloads Chrome for Testing on first run and exposes commands agents can call from a shell, including a snapshot command that returns the page's accessibility tree with element refs for subsequent actions. It installs via npm, Homebrew or Cargo, can be pinned as a project dependency, and is distributed as a skill on skills.sh.
Open sourcekeyword match
Agent Skills/agentskills · Python
Agent Skills is an open, lightweight format for extending agents with specialised knowledge and workflows. A skill is a folder containing a SKILL.md file with name and description metadata plus instructions, optionally bundling scripts, references and assets. Agents load skills by progressive disclosure: only names and descriptions at startup, the full SKILL.md when a task matches, and bundled files during execution. This repository holds the specification and documentation; agentskills.io lists compatible clients, and Anthropic's skills repo provides examples.
Open sourcekeyword match
Every/compound-engineering-plugin · TypeScript
Compound Engineering is Every's plugin of 36 skills for AI coding agents, organised around a loop of brainstorm, plan, build, review and capture what was learned, so knowledge from each change is written where the next change can use it. It runs on 14 agent hosts including Claude Code, Cursor and Codex, installed via each host's plugin marketplace. Skills such as ce-explain and ce-pov support understanding and recommendations. It is maintained by Kieran Klaassen and Trevin Chow with community contributions.
Open sourcekeyword match
SuperClaude-Org/SuperClaude_Framework · Python
SuperClaude describes itself as a meta-programming configuration framework that turns Claude Code into a structured development platform through behavioral instruction injection and component orchestration. The current v4.x line installs via pipx and ships 30 /sc:* slash commands, 20 specialized agents, 7 behavioral modes and optional MCP server installs (e.g. Tavily, Context7). A TypeScript plugin system is planned for v5.0. The project states it is not affiliated with or endorsed by Anthropic.
Open sourcekeyword match
siteboon/claudecodeui · TypeScript
CloudCLI, also known as Claude Code UI, is a free open-source web GUI for managing coding-agent sessions and projects remotely, supporting Claude Code, OpenCode, Cursor CLI and Codex. It provides a responsive desktop/mobile chat interface, an integrated shell, file and git explorers, browser sessions, session resume and history, and a plugin system for custom tabs and backend services. It can be self-hosted via npx or used as CloudCLI Cloud, a managed containerized development environment.
Open sourcekeyword match
agent-infra/sandbox · Python
AIO Sandbox packages a browser (with VNC), terminal, file system, VS Code Server, Jupyter and MCP into a single Docker container for AI agents, exposing them through one API on port 8080. It supports API-key authentication across its services, publishes pinned release images (including a mainland-China mirror), and documents cloud deployment behind a reverse proxy or ingress. The project links an accompanying arXiv paper and ships examples and an evaluation suite.
Open sourcekeyword match
OpenClaw/acpx · TypeScript
acpx is a headless command-line client for the Agent Client Protocol (ACP) from the OpenClaw organization. It gives agents, orchestrators and developers one structured interface for persistent, repository-scoped sessions, one-shot runs, permissions and machine-readable JSON output across ACP-compatible coding agents, with built-in profiles for Pi, OpenClaw, Codex and Claude Code plus custom ACP servers. It is distributed on npm, requires Node.js 22.13+, and is pre-1.0, so its CLI and runtime interfaces are still evolving.
Open sourcekeyword match
Strivex/paneflow · Rust
Paneflow is a GPL-3.0 terminal multiplexer for coding agents built with Rust and GPUI. It tracks whether each agent session is working, waiting for input or done, keeps sessions alive after quitting, and uses git worktrees for parallel tasks. A Changes tab offers side-by-side or unified diffs with block-level revert, a Files tab provides a lightweight editor, and a read-only MCP bridge lets agents read other panes' output, with a `paneflow` CLI for automation. It supports Claude Code, Codex, Gemini, opencode, Pi and other CLI tools.
Open sourcekeyword match
Asterisk/opcode · TypeScript
opcode is an AGPL-3.0 desktop application built with Tauri 2 that wraps Claude Code in a GUI. It manages Claude Code projects and interactive sessions, lets users create custom 'CC Agents' that can run as background agents, and adds a usage-analytics dashboard, MCP server management, session timeline and checkpoints, and CLAUDE.md editing. The README states it is an independent project not affiliated with Anthropic and links to the @getAsterisk X account.
Open sourcekeyword match
eyaltoledano/claude-task-master · JavaScript
Taskmaster is an AI-powered task-management system that plugs into coding-agent environments such as Cursor, Windsurf and Roo. The project homepage is tryhamster.com. It is licensed MIT with the Commons Clause.
Open sourcekeyword match
ccusage/ccusage · Rust
ccusage is a CLI that analyzes token usage and cost for Claude Code and Codex sessions from local logs, with a website at ccusage.com. The package is MIT licensed.
Open sourcekeyword match
davila7/claude-code-templates · Python
Claude Code Templates is a CLI tool for configuring and monitoring Claude Code, with a template marketplace at aitmpl.com. It is MIT licensed.
Open sourcekeyword match
Dicklesworthstone/mcp_agent_mail_rust · Rust
A Rust MCP server for coordinating multiple coding agents. It has 45 tools and 25 resources, a Git-backed archive, SQLite indexing, advisory file locks, a TUI, a web UI and an agent-first CLI. It is the maintained rewrite of the original Python mcp_agent_mail, which is now deprecated.
Open sourcekeyword match
github/github-mcp-server · Go
GitHub's official Model Context Protocol server. It exposes GitHub (repositories, issues, pull requests, Actions) as tools that MCP-compatible agents can call.
Open sourcekeyword match
microsoft/playwright-mcp · TypeScript
Microsoft's Model Context Protocol server for browser automation with Playwright. It lets agents drive a browser through MCP tools and is distributed as the npm package @playwright/mcp.
Open sourcekeyword match
yamadashy/repomix · TypeScript
Repomix packs an entire repository into a single AI-friendly file so the codebase can be fed to LLMs and AI tools such as Claude, ChatGPT and Gemini. It is a context-engineering tool for coding agents.
Open sourcekeyword match
amantus-ai/vibetunnel · TypeScript
VibeTunnel lets you use a web browser as a terminal, so you can control terminal-based coding agents remotely. Its homepage is vt.sh.
Open sourcekeyword match
VoltAgent/awesome-claude-code-subagents · Shell
A collection of 100+ specialized Claude Code subagents covering a wide range of development use cases. It is maintained by the VoltAgent organization.
Open sourcekeyword match
github/awesome-copilot · JavaScript
A GitHub-maintained repository of community-contributed instructions, agents, skills and configurations to help you get the most out of GitHub Copilot. It has a companion website at awesome-copilot.github.com.
Open sourcekeyword match
anthropics/claude-plugins-official · Python
An official, Anthropic-managed directory of high-quality Claude Code plugins. It acts as the plugin marketplace for extending the Claude Code harness, and its plugin documentation is at code.claude.com.
Open sourcekeyword match
jarrodwatts/claude-hud · JavaScript
Claude HUD is a Claude Code plugin that shows context usage, active tools, running agents and todo progress as a session runs.
Open sourcekeyword match
sirmalloc/ccstatusline · TypeScript
ccstatusline is a highly customizable statusline for the Claude Code CLI, with powerline support and themes. It shows session information in the Claude Code terminal UI.
Open sourcekeyword match
wonderwhy-er/DesktopCommanderMCP · JavaScript
Desktop Commander is an MCP server for Claude that adds terminal control, file system search and diff-based file editing. With it, an MCP client such as Claude Desktop can act as a local coding and automation agent. It has a website at desktopcommander.app.
Open sourcekeyword match
BeehiveInnovations/pal-mcp-server · Python
PAL MCP Server, formerly Zen MCP, is an MCP server that connects Claude Code, Gemini CLI and Codex CLI to other model providers. These include Gemini, OpenAI, OpenRouter, Azure, Grok, Ollama and custom models. It lets a coding agent consult other models within one workflow.
Open sourcekeyword match
UfoMiao/zcf · TypeScript
ZCF (Zero-Config Code Flow) is a zero-configuration setup and workflow toolkit for Claude Code and Codex. It has a website at zcf.ufomiao.com.
Open sourcekeyword match
openclaw/clawhub · TypeScript
ClawHub is the skill and plugin registry for the OpenClaw personal agent, run from the openclaw GitHub organization. It is hosted at clawhub.ai.
Open sourcekeyword match
mufeedvh/code2prompt · Rust
A CLI tool that turns a codebase into a single LLM prompt. The prompt includes a source tree, and the tool also offers prompt templates and token counting.
Open sourcekeyword match
coderamp-labs/gitingest · Python
Gitingest turns any GitHub repository into a prompt-friendly text extract. To use it, replace 'hub' with 'ingest' in the GitHub URL. It is available as a hosted site and as an open-source Python package.
Open sourcekeyword match
Pimzino/spec-workflow-mcp · TypeScript
An MCP server with tools for a structured, spec-driven development workflow in AI-assisted software development. It includes a real-time web dashboard and a VS Code extension for tracking project progress.
Open sourcekeyword match
genkit-ai/genkit · TypeScript
Genkit is an open-source framework for building agentic apps in JavaScript, Go, Dart and Python. It is built and used in production by Google and is Apache-2.0 licensed.
Open sourcekeyword match
QwenLM/Qwen-Agent · Python
Agent framework and applications built upon Qwen>=3.0. Features function calling, MCP, a code interpreter, RAG and a Chrome extension.
Open sourcekeyword match
Agenta-AI/agenta · TypeScript
Open-source workspace where you build specialized agents by chatting with them. You connect apps through MCP or Composio and improve agents through feedback. Agents can be used in the web app, Slack, Telegram or WhatsApp Business, and can run as scheduled or event-triggered automations with per-run visibility. The README states it is MIT-licensed.
Open sourcekeyword match
modelcontextprotocol/servers · TypeScript
The official collection of Model Context Protocol reference servers, maintained by the MCP project.
Open sourcekeyword match
modelcontextprotocol/inspector · TypeScript
MCP Inspector is the official MCP project tool for testing and debugging MCP servers.
Open sourcekeyword match
modelcontextprotocol/registry · Go
A community-driven registry service for Model Context Protocol servers, run under the official modelcontextprotocol organization.
Open sourcekeyword match
ChromeDevTools/chrome-devtools-mcp · TypeScript
Chrome DevTools MCP gives coding agents access to Chrome DevTools via MCP. It is maintained by the ChromeDevTools team.
Open sourcekeyword match
googleapis/mcp-toolbox · Go
MCP Toolbox for Databases is an open-source MCP server for databases, maintained in the googleapis GitHub organization.
Open sourcekeyword match
IBM/mcp-context-forge · Python
An AI gateway, registry and proxy that sits in front of any MCP, A2A or REST/gRPC API and exposes a unified endpoint with centralized discovery, guardrails and management. It supports plugins.
Open sourcekeyword match
docker/mcp-gateway · Go
Docker's MCP CLI plugin and MCP Gateway.
Open sourcekeyword match
metatool-ai/metamcp · TypeScript
MetaMCP is an MCP aggregator, orchestrator, middleware and gateway shipped as a single Docker image.
Open sourcekeyword match
samanhappy/mcphub · TypeScript
MCPHub is an open-source, self-hosted MCP gateway and control plane for connecting, controlling, and operating MCP servers. It is distributed via npm (@samanhappy/mcphub) and Docker.
Open sourcekeyword match
sparfenyuk/mcp-proxy · Python
mcp-proxy is a bridge between the Streamable HTTP and stdio MCP transports, letting clients and servers that use different transports talk to each other.
Open sourcekeyword match
Klavis-AI/klavis · Python
Klavis AI provides MCP integration platforms that let AI agents use tools reliably at any scale. The repo includes MCP integrations, an MCP sandbox, and Strata, described as one MCP server for agents to handle thousands of tools.
Open sourcekeyword match
MCP-UI-Org/mcp-ui · TypeScript
MCP-UI is a protocol extension and SDK for delivering interactive UI experiences over the Model Context Protocol.
Open sourcekeyword match
higress-group/higress · Go
Higress is an AI-native API gateway whose AI capabilities support mainstream model providers. It hosts MCP servers through its plugin mechanism, can convert OpenAPI specs into remote MCP servers with openapi-to-mcp, and gives unified management of LLM APIs and MCP APIs.
Open sourcekeyword match
nlweb-ai/NLWeb · Python
NLWeb is the main reference implementation for building conversational interfaces for websites. It supports MCP natively: every NLWeb instance acts as an MCP server with an `ask` method, so the same natural-language API serves both people and AI agents.
Open sourcekeyword match
nanobrowser/nanobrowser · TypeScript
Nanobrowser is an open-source AI agent for web automation. It runs in your own logged-in browser to automate daily tasks.
Open sourcekeyword match
microsoft/OmniParser · Jupyter Notebook
OmniParser is Microsoft's screen-parsing tool. It turns screenshots into structured elements so that vision-only GUI agents can act on them.
Open sourcekeyword match
OthersideAI/self-operating-computer · Python
Self-Operating Computer is a framework from OthersideAI that lets a multimodal model operate a computer. The model reads the screen and controls the keyboard and mouse.
Open sourcekeyword match
web-infra-dev/midscene · TypeScript
Midscene.js is vision-driven UI automation driven by natural language. The repo describes it as E2E testing in natural language.
Open sourcekeyword match
JuliusBrussee/caveman · Go
Caveman makes coding agents answer tersely and read less, which it says cuts about 65% of tokens. One npx install sets up the skill and a local proxy, so plain claude, Codex, Gemini CLI, OpenCode and 30+ other agents stay caveman'd. Each of its six parts has its own switch, and the skill can be installed without the proxy.
Open sourcekeyword match
yusufkaraaslan/Skill_Seekers · Python
Skill Seekers turns documentation websites, GitHub repositories and PDFs into Claude skills, and flags conflicts between sources. It installs from pip, has an optional MCP server, and can package skills for Cursor, Windsurf, Cline and other agents.
Open sourcekeyword match
tigerless-labs/autoharness · Python
A Claude Code plugin that distills new skills from your real sessions and keeps them updated as you work. It uses hooks and an MCP server, and it only changes skills it generated itself. Install it from its plugin marketplace.
Open sourcekeyword match
anthropics/claude-plugins-community · JavaScript
Anthropic's community plugin marketplace for Claude Code and Claude Cowork. This repo is a read-only mirror; plugins are submitted through Anthropic's directory form.
Open sourcekeyword match
obra/superpowers-marketplace · See repository
obra's curated Claude Code plugin marketplace, which distributes Superpowers and related plugins.
Open sourcekeyword match
Haleclipse/CCometixLine · Rust
A Claude Code statusline tool written in Rust.
Open sourcekeyword match
Owloops/claude-powerline · TypeScript
A vim-style powerline statusline for Claude Code.
Open sourcekeyword match
mohak34/opencode-notifier · TypeScript
An OpenCode plugin that plays desktop notifications and sounds on permission requests, task completion and errors.
Open sourcekeyword match
slkiser/opencode-quota · TypeScript
Shows OpenCode quota and token usage across many providers (Copilot, Cursor, OpenAI, Kimi, Antigravity, Z.ai and more) without using any context window.
Open sourcekeyword match
PeonPing/peon-ping · Shell
Warcraft III peon voice notifications for Claude Code, Codex, IDEs and other AI agents, so you don't have to keep watching the terminal.
Open sourcekeyword match
backnotprop/plannotator · TypeScript
Lets you annotate and review coding-agent plans and diffs visually, share them with your team, and send feedback to the agent in one click.
Open sourcekeyword match
CloudAI-X/claude-workflow-v2 · Python
Universal Claude Code workflow plugin with agents, skills, hooks, and commands.
Open sourcekeyword match
agent-sh/agentsys · JavaScript
AI writes code; AgentSys automates everything else with 24 plugins, 49 agents and 44 skills for Claude Code, OpenCode, Codex, Cursor and Kiro.
Open sourcekeyword match
numman-ali/n-skills · TypeScript
Curated skill marketplace for AI agents built on the universal SKILL.md format and the openskills installer; works with Claude Code, Codex and others.
Open sourcekeyword match
Microsoft/apm · Python
Agent Package Manager: installs and versions context packages (skills, prompts, plugins) for Copilot, Claude Code, Codex and other agents.
Open sourcekeyword match
first-fluke/oh-my-agent · TypeScript
Load one skill or install domain presets, project hooks and parallel workflows with test gates across Claude Code, Codex, Cursor and others.
Open sourcekeyword match
sangrokjung/claude-forge · Shell
One-install Claude Code configuration pack with agents, commands, skills, safety hooks and an adversarial review loop.
Open sourcekeyword match
Gentleman-Programming/gentle-ai · Go
Gentle-AI configures Claude Code, Cursor, OpenCode, Codex, Pi and more with persistent memory, curated skills, MCP servers, personas and optional review, with no agent lock-in.
Open sourcekeyword match
severity1/claude-code-prompt-improver · Python
Prompt-improver hook for Claude Code: type vibes, ship precision.
Open sourcekeyword match
disler/claude-code-hooks-multi-agent-observability · Python
Real-time monitoring for Claude Code agents through simple hook event tracking.
Open sourcekeyword match
carlrannaberg/claudekit · TypeScript
A toolkit of custom commands, hooks and utilities for Claude Code.
Open sourcekeyword match
pchalasani/claude-code-tools · Python
Practical productivity tools (tmux, session/context utilities, hooks) for Claude Code, Codex CLI and similar agents.
Open sourcekeyword match
runkids/skillshare · Go
CLI that syncs skills, agents, MCP servers and plugins to all AI CLI tools and makes team sharing simpler.
Open sourcekeyword match
Jia-Ethan/codex-keysmith · Python
Versioned Codex instruction deployment with previews, ownership manifests, hook isolation, scenario evaluation and recovery. The repo is young (created June 2026, few commits and watchers against many forks), so treat its star count with caution.
Open sourcekeyword match
openai/skills · Python
OpenAI's official catalog of Agent Skills for Codex.
Open sourcekeyword match
huggingface/skills · Python
Official skills for using Hugging Face models, datasets, training and Spaces from coding agents.
Open sourcekeyword match
google-gemini/gemini-skills · Python
Official skills for the Gemini API, its SDKs and model/agent interactions.
Open sourcekeyword match
browserbase/skills · JavaScript
Browserbase's official agent skills that give agents access to the web.
Open sourcekeyword match
SawyerHood/dev-browser · TypeScript
A Claude skill that lets your agent use a web browser.
Open sourcekeyword match
lackeyjb/playwright-skill · JavaScript
General-purpose Playwright browser-automation skill for coding agents.
Open sourcekeyword match
sickn33/agentic-awesome-skills · Python
Local control plane for agents to discover, select and validate skills from a catalog of 2,750+. Ships a CLI, a local MCP server, plugins and a Workbench.
Open sourcekeyword match
openai/plugins · JavaScript
OpenAI's official collection of plugins for the Codex harness.
Open sourcekeyword match
cursor/plugins · TypeScript
The Cursor plugin specification plus Cursor's own official plugins.
Open sourcekeyword match
cursor/community-plugins · TypeScript
Plugins contributed by the Cursor community, published at cursor.directory.
Open sourcekeyword match
github/copilot-plugins · PowerShell
GitHub's official Copilot plugin collection of MCP servers, skills, hooks and other extensions.
Open sourcekeyword match
jeremylongshore/tons-of-skills-marketplace · Python
Agent-skills platform with a harness-free canonical layer, verified adapters for each harness and the ccpi package manager.
Open sourcekeyword match
davepoon/buildwithclaude · Python
A single hub for finding Claude skills, agents, commands, hooks, plugins and marketplace collections for Claude Code, Claude Desktop, the Agent SDK and OpenClaw.
Open sourcekeyword match
ananddtyagi/cc-marketplace · Python
Community-run marketplace repo for Claude Code plugins.
Open sourcekeyword match
Piebald-AI/tweakcc · TypeScript
Patches Claude Code to customise system prompts, create custom toolsets, add input highlighters, themes and spinners, support AGENTS.md and unlock unreleased features.
Open sourcekeyword match
kdcokenny/ocx · TypeScript
OpenCode extension manager that packages your setup into portable, isolated profiles you can carry anywhere.
Open sourcekeyword match
chongdashu/cc-statusline · TypeScript
Generates an informative Claude Code statusline with model, cost, context usage and git details.
Open sourcekeyword match
rz1989s/claude-code-statusline · Shell
Shell-based Claude Code statusline with flexible layouts, themes, real-time cost tracking and MCP monitoring.
Open sourcekeyword match
snipeship/ccflare · TypeScript
Proxy for Claude Code that balances requests across accounts and provides an analytics dashboard.
Open sourcekeyword match
kaitranntt/ccs · TypeScript
Provider and account switcher for Claude Code via CLIProxyAPI OAuth proxy, with visual dashboard and remote proxy support.
Open sourcekeyword match
foreveryh/claude-code-switch · Shell
Shell tool to switch Claude Code between Anthropic-API-compatible models and providers in one command.
Open sourcekeyword match
dyoshikawa/rulesync · TypeScript
CLI that keeps a single source of rules, commands, subagents and MCP config in sync across many coding agents.
Open sourcekeyword match
intellectronica/ruler · TypeScript
Centralizes agent instructions and distributes them into each coding agent's config files.
Open sourcekeyword match
nicobailon/pi-subagents · TypeScript
Pi extension for async subagent delegation with truncation, artifacts and session sharing.
Open sourcekeyword match
feiskyer/claude-code-settings · Python
Curated skills, sub-agents and config templates for Claude Code: research, image generation, GitHub automation and more.
Open sourcekeyword match
trailofbits/claude-code-config · Shell
Opinionated defaults, documentation and workflows for Claude Code as used at Trail of Bits.
Open sourcekeyword match
fcakyon/claude-codex-settings · Python
Battle-tested Claude Code, OpenAI Codex and Cursor configs, plugins, hooks and agents, with Kimi, MiniMax and GLM API support.
Open sourcekeyword match
diet103/claude-code-infrastructure-showcase · TypeScript
Examples of a Claude Code infrastructure with skill auto-activation, hooks and agents.
Open sourcekeyword match
ChrisWiles/claude-code-showcase · JavaScript
Claude Code project configuration example with hooks, skills, agents, commands and GitHub Actions workflows.
Open sourcekeyword match
centminmod/my-claude-code-setup · Python
Shared starter template configuration and CLAUDE.md memory bank system for Claude Code.
Open sourcekeyword match
tiann/hapi · TypeScript
Remote and mobile app for running Codex, Claude Code, Pi, OpenCode, Kimi Code and Grok Build sessions anywhere.
Open sourcekeyword match
Ark0N/Codeman · TypeScript
Self-hosted mission control to run Claude Code, OpenCode, Pi, Codex, Antigravity and Gemini CLI 24/7 from any device and watch subagents live.
Open sourcekeyword match
wasabeef/claude-code-cookbook · Shell
A collection of settings, commands, roles and hooks to make Claude Code more useful.
Open sourcekeyword match
qdhenry/Claude-Command-Suite · Shell
Slash commands and agents for structured workflows: code review, feature creation, security auditing and architecture analysis.
Open sourcekeyword match
peterkrueck/Claude-Code-Development-Kit · Shell
Claude Code workflow for beginners and intermediate users, with a tiered documentation/context system, hooks, MCP integration and an installer.
Open sourcekeyword match
GWUDCAP/cc-sessions · JavaScript
Opinionated Claude Code hooks and workflow that enforce discussion-before-implementation task sessions.
Open sourcekeyword match
junhoyeo/tokscale · Rust
Rust CLI that tracks token usage across coding agents and publishes a global leaderboard.
Open sourcekeyword match
hoangsonww/Claude-Code-Agent-Monitor · TypeScript
Monitoring dashboard (SQLite, Express, React) tracking sessions, subagent orchestration and tool usage for Claude Code and Codex.
Open sourcekeyword match
d-kimuson/claude-code-viewer · TypeScript
Full-featured web-based Claude Code client for managing and running Claude Code projects and sessions.
Open sourcekeyword match
coleam00/context-engineering-intro · Python
Context-engineering template with the PRP workflow, commands and CLAUDE.md conventions for AI coding assistants, centered on Claude Code.
Open sourcekeyword match
Palgu/clawalkietalkie-plugin · TypeScript
The MIT-licensed client half of clawalkietalkie. The Claude Code mod gives a session a cc: address and starts a turn when a message arrives; the MCP server lets Codex, Cursor, Copilot, Gemini CLI and Claude apps send messages, read their inbox and set their status; the GitHub Action lets a workflow message an agent and wait for its reply. The clients talk to the hosted relay at api.clawalkietalkie.com.
Open sourcekeyword match
ZHangZHengEric/Sage · Python
Sage is an MIT-licensed agent harness for developers using Desktop, Server/Studio or the SAgents Python runtime. It supports versioned agent packages, persistent sessions, streamed output, tools, Skills, MCP and multi-agent workflows. Its RSI workflow uses goals or curated history to produce candidate versions with evaluation evidence; users choose whether to adopt them. Desktop RSI currently supports simple types and native tools, not every general MCP integration. Built-in configurations target one process or host; Server supports one worker. Local execution is not container isolation, and persistent state does not provide distributed job takeover or automatic checkpoint resume. AI-assisted submission on behalf of the maintainer, based on the official README; no independent testing is claimed.
Open sourcekeyword match
OpenMontageInc/OpenMontage · Python
OpenMontage is an open-source agentic video production system for coding assistants such as Claude, Copilot, and Cursor. It includes 12 production pipelines, 100+ tools, and 700+ agent skill and production-knowledge files.
Open sourcekeyword match
Mintplex-Labs/anything-llm · JavaScript
Local-first application for running a private agent setup, including RAG, multimodal input, computer use, and agent orchestration. It is self-hosted rather than a rented hosted service.
Open sourcekeyword match
CherryHQ/cherry-studio · TypeScript
Open-source AI workspace for models, agents, and productivity. Topics include an MCP client, agent skills, computer use, RAG, and Ollama.
Open sourcekeyword match
VectifyAI/PageIndex · Python
Document index for vectorless, reasoning-based retrieval-augmented generation. Topics include agents, context engineering, information retrieval, and RAG.
Open sourcekeyword match
CopilotKit/CopilotKit · TypeScript
Open-source frontend stack for agents and generative UI, with support for React, Angular, mobile, and Slack. The project also makes the AG-UI protocol.
Open sourcekeyword match
DayuanJiang/next-ai-draw-io · TypeScript
Web app, desktop app, and MCP server for drawing and editing draw.io diagrams by chatting with an AI. The MCP server targets Claude Code, Cursor, Codex, and VS Code.
Open sourcekeyword match
assafelovic/gpt-researcher · Python
GPT Researcher is an autonomous Python agent that conducts deep research on any data using any LLM provider. The Apache-2.0 project includes search, web scraping, and MCP server support.
Open sourcekeyword match
activepieces/activepieces · TypeScript
Activepieces is an open-source TypeScript project for workflow automation with AI agents and MCP servers. The repository describes about 400 MCP servers for AI agents and presents the project as an n8n alternative.
Open sourcekeyword match
modelcontextprotocol/python-sdk · Python
The official Python SDK for Model Context Protocol servers and clients. It is the library for building MCP servers and clients in Python.
Open sourcekeyword match
czlonkowski/n8n-mcp · TypeScript
An MCP server that lets Claude, ChatGPT, Cursor, and other AI assistants operate n8n. It supports debugging, editing, validating, testing, and building workflows on any n8n instance.
Open sourcekeyword match
1Panel-dev/MaxKB · Python
MaxKB is an open-source platform for building enterprise-grade agents. Project topics include knowledge bases, RAG, LangChain, and an MCP server.
Open sourcekeyword match
xerj-org/xerj · Rust
A single Rust binary that indexes code, docs, logs, JSONL/CSV, and PDFs for BM25, vector, and hybrid search. It exposes an MCP server and an Elasticsearch-compatible API, and Corpus Hub serves reference memory corpora.
Open sourcekeyword match
xpzouying/xiaohongshu-mcp · Go
Go MCP server for xiaohongshu.com. Apache-2.0 licensed, with repository topics limited to MCP and this platform.
Open sourcekeyword match
apify/apify-mcp-server · TypeScript
TypeScript MCP server that lets AI agents extract data from social media, search engines, maps, e-commerce, and other sites using scrapers, crawlers, and automation tools from the Apify Store. MIT licensed.
Open sourcekeyword match
raga-ai-hub/RagaAI-Catalyst · Python
Python SDK for agent observability, monitoring, and evaluation. It includes agent, LLM, and tool tracing, multi-agent debugging, a self-hosted dashboard, and analytics with timeline and execution-graph views. Apache-2.0 licensed.
Open sourcekeyword match
NanmiCoder/cc-haha · TypeScript
cc-haha is a local-first, cross-platform desktop workspace for Claude Code and AI agents. It includes multi-agent collaboration, Git worktrees, code diffs, a skills marketplace, multi-model support, and Computer Use. Remote access is described via WeChat, Feishu, DingTalk, Telegram, WhatsApp, and H5.
Open sourcekeyword match
modelcontextprotocol/typescript-sdk · TypeScript
The official TypeScript SDK for Model Context Protocol servers and clients. It is the library for implementing MCP in TypeScript.
Open sourcekeyword match
mrexodia/ida-pro-mcp · Python
ida-pro-mcp bridges IDA Pro with language models through MCP. It is an IDA plugin for AI-assisted reverse engineering and binary analysis.
Open sourcekeyword match
tadata-org/fastapi_mcp · Python
fastapi_mcp exposes FastAPI endpoints as Model Context Protocol tools and includes authentication. Topics cover MCP servers, OpenAPI, and clients such as Claude, Cursor, and Windsurf.
Open sourcekeyword match
cobusgreyling/loop-engineering · TypeScript
loop-engineering provides patterns, starters, and CLI tools for loop engineering with AI coding agents. Named tools include loop-audit, loop-init, and loop-cost, for systems that prompt and orchestrate agents.
Open sourcekeyword match
Agents365-ai/drawio-skill · Python
drawio-skill is an agent skill that turns natural language, code, and sources such as Terraform, Kubernetes, SQL, and OpenAPI into editable draw.io architecture diagrams. It lists incremental sync, drift diff, CI architecture tests, and Claude Code and MCP support.
Open sourcekeyword match
mobile-next/mobile-mcp · TypeScript
Mobile MCP is an MCP server that lets AI agents drive iOS and Android apps on simulators, emulators, and real devices. It works with Claude Code, Codex, Cursor, and any MCP client.
Open sourcekeyword match
awslabs/mcp · Python
Open-source MCP servers for AWS from awslabs. The project is Python, Apache-2.0 licensed, and includes MCP server and client tooling, with docs on the project site.
Open sourcekeyword match
Fei2411/DS-Bot · JavaScript
DS-Bot is a JavaScript plugin for DeepSeek Harness that runs teams of long-lived bots. It includes main bots, bot-to-bot messages, and group chats.
Open sourcekeyword match
vastsa/PI-Desktop · TypeScript
PI-Desktop is a local-first AI coding agent desktop. It uses Electron, a Rust host core, and the pi Agent Harness, and supports user-installable plugins and MCP.
Open sourcekeyword match
BuilderIO/agent-native · TypeScript
agent-native is an MIT-licensed TypeScript framework from BuilderIO for building agentic apps. Topics include agent frameworks, MCP, React, and generative UI.
Open sourcekeyword match
gepa-ai/gepa · Jupyter Notebook
GEPA applies reflective optimization to prompts, code, and other artifacts. Topics include harness engineering, agent skills, coding agents, and LLM evaluation.
Open sourcekeyword match
microsoft/TokenEconomizer · Python
Python project for experience-driven, black-box cost control of coding agents, including Claude Code, Codex, and GitHub Copilot. It targets token use and cost reduction. Apache-2.0, from Microsoft.
Open sourcekeyword match
kajisho5/ffmpeg-skill · Python
Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor, and Codex. Covers cut, captions, reframe, loudness, and platform exports. No cloud and no API keys.
Open sourcekeyword match
KunAgent/Kun · TypeScript
Kun is a local-first AI agent workspace for coding, writing, design, research, and automation. It uses one runtime for a desktop GUI and a TUI, and its topics include MCP, multi-agent workflows, and coding agents. It is written in TypeScript.
Open sourcekeyword match
ModelEngine-Group/nexent · Python
Nexent is an open-source zero-code platform for auto-generating AI agents using harness engineering principles. It unifies tools, skills, memory, and orchestration, with constraints, feedback loops, and control planes. It is written in Python under the MIT license.
Open sourcekeyword match
microsoft/CUAWright · Python
CUAWright is a Python framework for browser and desktop agents, described as a simple SWE-style framework for long-horizon computer-use tasks. It is published by Microsoft under the MIT license.
Open sourcekeyword match
rllm-org/rllm · Python
Open-source Python project for reinforcement learning with LLMs. Topics include agent frameworks, agentic workflows, coding agents, SWE agents, search agents, and distributed training. Licensed under Apache-2.0.
Open sourcekeyword match
areal-project/AReaL · Python
Open-source Python project described as an RL bridge for LLM-based agent applications. Topics include agents, LLM reasoning, machine-learning systems, and reinforcement learning. Licensed under Apache-2.0.
Open sourcekeyword match
ApodexAI/FrontierAgent · Python
Open-source agent framework with a native command-line TUI, ReAct and Agent Team modes. It is started with one command on macOS and Linux, with no preinstall and no hard Docker dependency.
Open sourcekeyword match
sandbox-quantum/switch · Python
Open-source AI teammates for Slack, Teams, Discord, Telegram, and Mattermost. It is self-hosted and works with any agent harness and any model.
Open sourcekeyword match
spacering-net/codeg · Rust
Collaborative coding workspace that aggregates sessions from Claude Code, Codex, OpenCode, Pi, Grok Build, and similar agents. It can run as a desktop app, a self-hosted server, or Docker, and is written in Rust under Apache-2.0.
Open sourcekeyword match
JetBrains/go-modern-guidelines · Go
Apache-2.0 guidelines from JetBrains meant to help AI coding agents write modern Go. The repository is agent-facing language guidance rather than a runtime.
Open sourcekeyword match
tutti-os/tutti · TypeScript
TypeScript desktop app for people and agents to work in a shared, local-first workspace. Topics cover multi-agent orchestration, MCP, and coding agents such as Claude Code and Codex. Apache-2.0.
Open sourcekeyword match
golutra/golutra · Rust
Rust platform that combines Codex, Claude Code, and OpenClaw into one agent system with parallel execution, task orchestration, and long-running workflows. It is aimed at automation and developer workflows, and ships as a desktop app.
Open sourcekeyword match
SeemSeam/claude_codex_bridge · Python
Python CLI workspace for running Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other coding agents together in one visible multi-agent session.
Open sourcekeyword match
michael-denyer/pstack-claude · TypeScript
Claude Code, Codex, Copilot, Pi, OpenCode, Muse, Gemini, and Prime Agent versions of Poteto's pstack. Translates Cursor workflow primitives into agent workflows for those harnesses.
Open sourcekeyword match
yilewang/llm-for-zotero · TypeScript
An open-source research agent system for a Zotero library. Repository topics include MCP, RAG, Codex, literature analysis, and a Zotero plugin.
Open sourcekeyword match
QwenLM/Qwen-MM-Plugins · Python
QwenLM project described as making any agent harness multimodal-native. It is a Python project under Apache-2.0.
Open sourcekeyword match
fuxicodex/Fuxi · Python
FuXi is a self-contained terminal AI coding agent for editing code, running commands, and driving tools. It includes cost-aware routing across LLM providers and lists MCP among its topics.
Open sourcekeyword match
Pinvou/pinvou-agent · Rust
pinvou-agent is an open-source desktop AI agent for tools, files, knowledge, workflows, and deliverables. Topics include a Rust app, MCP client support, local-first use, and Ollama.
Open sourcekeyword match
cocoindex-io/cocoindex-code · Python
cocoindex-code is a lightweight embedded code search CLI that indexes code with an AST-based approach. It is aimed at faster context retrieval for coding agents, and MCP is among its topics.
Open sourcekeyword match
teaql/teaql-agent-kit · TypeScript
A model-driven harness for AI coding agents. It covers semantic modeling, app generation, progressive API assist, and evidence-based verification.
Open sourcekeyword match
itayinbarr/little-coder · TypeScript
A harness optimized for smaller LLMs and coding agents. Topics cover local models, Ollama, tool use, and Terminal-Bench.
Open sourcekeyword match
NeuralNomadsAI/CodeNomad · TypeScript
A desktop app described as a command center for AI coding. It is a TypeScript project whose topics include coding agents, OpenCode, Electron, and Tauri.
Open sourcekeyword match
CoderLuii/HolyClaude · JavaScript
An AI coding workstation that combines Claude Code, a web UI, eight AI CLIs, a headless browser, and more than 50 tools.
Open sourcekeyword match
amElnagdy/delegate-skills · JavaScript
Skills for delegating a coding task to a separate coding agent CLI, reviewing the diff, and landing the commit yourself. They are split one per implementer and target CLIs such as Claude Code, Codex, Cursor, and OpenCode.
Open sourcekeyword match
Weizhena/Deep-Research-skills · Python
A structured deep research skill for Claude Code, OpenCode, and Codex, with human-in-the-loop control.
Open sourcekeyword match
obsidianmd/obsidian-skills · Shell
Skills from the Obsidian project that teach coding agents to use the Obsidian CLI and open formats, including Markdown, Bases, and JSON Canvas. Usable with Claude Code, Codex, OpenCode, Cursor, and other harnesses.
Open sourcekeyword match
googleworkspace/cli · Rust
A Rust command-line tool for Google Workspace services including Drive, Gmail, Calendar, Sheets, Docs, Chat, and Admin, built from the Google Discovery Service. It includes AI agent skills and a Gemini CLI extension so agents can call those APIs.
Open sourcekeyword match
citrolabs/ego-lite · JavaScript
A browser for AI-agent browser automation that can share a logged-in browser session with coding agents such as Codex or Claude Code. It is published as an agent skill for those harnesses.
Open sourcekeyword match
777genius/agent-teams-ai · TypeScript
TypeScript app where agents take tasks, message each other, and review work while the user directs them from a kanban board. It names support for Codex, Claude, OpenCode, Cursor, and other coding-agent runtimes.
Open sourcekeyword match
Sahir619/fable-method · Python
fable-method distills how Claude Fable 5 worked into skills any model can run, plus an eval. It targets coding-agent workflows with a think, act, and prove loop and is MIT-licensed Python.
Open sourcekeyword match
OpenCoworkAI/open-cowork · TypeScript
open-cowork is an MIT-licensed desktop app for Windows and macOS that one-click installs Claude Code, MCP tools, and skills. It includes sandbox isolation, multi-model support, and Feishu and Slack integration.
Open sourcekeyword match
neuron-core/neuron-ai · PHP
Neuron AI is an agentic framework for the PHP ecosystem for building AI-driven applications. It connects LLMs, tools, vector databases, and memory to agents that interact with application data and UI.
Open sourcekeyword match
peteromallet/dataclaw · Python
Dataclaw is an agent harness for publishing agent chat history as Hugging Face datasets. It is written in Python and released under the MIT license.
Open sourcekeyword match
Core-Mate/OpenGUI · HTML
OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps through the GUI.
Open sourcekeyword match
bubbuild/bub · Python
bub is a tiny Python agent runtime that is composable with plugins and can be self-hosted. It is licensed under Apache-2.0 and described as a harness.
Open sourcekeyword match
AgentEra/Agently · Python
Agently is a Python framework for building GenAI applications and interacting with agents in code through structured data and chained calls. It uses an event-driven flow, TriggerFlow, for working logic and can switch models without rewriting application code. It is licensed under Apache-2.0.
Open sourcekeyword match
codeaholicguy/ai-devkit · TypeScript
TypeScript project described as a control plane for AI coding agents. Repository topics include Claude Code, Codex CLI, Cursor, Gemini CLI, OpenCode, MCP, and memory. Licensed Apache-2.0.
Open sourcekeyword match
langwatch/better-agents · TypeScript
TypeScript project from LangWatch described as standards for building agents. Topics include agent testing, a CLI, MCP, and LLMOps. MIT-licensed.
Open sourcekeyword match
autonomous-ai/openharness · TypeScript
OpenHarness is an open-source TypeScript harness for managing multiple coding agents across machines from one command center. Its topics include Claude Code, Codex, OpenCode, tmux and MCP, and it extends to areas such as CAD, circuits and robotics.
Open sourcekeyword match
inkeep/agents · TypeScript
Inkeep Agents is a self-hostable platform for creating AI agents and multi-agent workflows, using either a no-code visual builder or a TypeScript SDK that stay in sync. It includes MCP support and developer SDK tooling.
Open sourcekeyword match
thClaws/thClaws · Rust
thClaws is an open-source AI agent harness written in Rust. One binary provides GUI, CLI, headless, and webapp interfaces, with multi-provider support, MCP, skills, plugins, and agent teams.
Open sourcekeyword match
Chorus-AIDLC/Chorus · TypeScript
Chorus is an agent harness for AI-human collaboration, inspired by the AI-Driven Development Lifecycle. The TypeScript project covers multi-agent work, Claude Code, and kanban-style task management, and is licensed AGPL-3.0.
Open sourcekeyword match
teng-lin/notebooklm-py · Python
Unofficial Python API and agent skill for Google NotebookLM. It provides programmatic access, including features the web UI does not expose, through Python, a CLI, and agents such as Claude Code, Codex, and OpenClaw.
Open sourcekeyword match
microsoft/SkillOpt · Python
Text-space optimizer that trains reusable natural-language skills for frozen LLM agents. It applies trajectory-driven edits and validation-gated updates, and emits a deployable best_skill.md artifact.
Open sourcekeyword match
muratcankoylan/Agent-Skills-for-Context-Engineering · Python
Collection of agent skills for context engineering, multi-agent architectures, and production agent systems. Intended for building, optimizing, or debugging agent systems that depend on effective context management.
Open sourcekeyword match
larksuite/cli · Go
Official Lark/Feishu CLI maintained by the larksuite team, built for humans and AI agents. It covers Messenger, Docs, Base, Sheets, Calendar, Mail, Tasks, Meetings, and other domains, with 200+ commands and 20+ AI agent skills.
Open sourcekeyword match
AgriciDaniel/claude-obsidian · Python
A Claude Code plugin that files sources into a connected knowledge graph of plain Markdown in Obsidian. Claude reads, links, and files notes the user owns. Based on Karpathy's LLM Wiki pattern for personal knowledge management.
Open sourcekeyword match
Orchestra-Research/AI-Research-SKILLs · TeX
A library of AI research and engineering skills packaged for Claude Code, Codex and Gemini CLI. Covers topics such as GRPO, vLLM, Megatron and Hugging Face. Maintained by Orchestra Research under the MIT license.
Open sourcekeyword match
nicobailon/visual-explainer · JavaScript
An agent skill that generates rich HTML pages or slide decks for diagrams, diff reviews, plan audits, data tables, and project recaps. It is a JavaScript project under the MIT license and is marked for any harness.
Open sourcekeyword match
JetBrains/thinkrail · TypeScript
ThinkRail is a JetBrains project described as an agentic IDE and a pi-agent extension. The TypeScript repo is Apache-2.0 and tagged for agent workflows and spec-driven development.
Open sourcekeyword match
firecrawl/firecrawl-mcp-server · JavaScript
Official MCP server for Firecrawl, described as a context API for AI agents. It exposes search, scrape, parse, crawl, map, agent, and monitor tools to MCP clients including Claude Code and Gemini CLI.
Open sourcekeyword match
xingkongliang/skills-manager · Rust
A lightweight desktop app, written in Rust, for managing, syncing and organizing AI agent skills across coding tools such as Claude Code, Codex, Cursor, Copilot and Gemini CLI.
Open sourcekeyword match
refly-ai/refly · TypeScript
Refly lets you define skills through a workflow approach and run them on Claude Code, Cursor, Codex and other agents. It can also expose them as APIs or Slack and Lark/Feishu bots.
Open sourcekeyword match
alchaincyf/darwin-skill · HTML
Autoresearch-inspired skill optimization for Claude Code, Codex, OpenClaw, and other harnesses. It evaluates a skill, improves it, tests the change, and keeps or reverts the result.
Open sourcekeyword match
jacob-bd/gemini-notebook-mcp-cli · Python
Python project that exposes Gemini Notebook through a command-line interface, a Model Context Protocol server, and AI agent skills. It is aimed at the Gemini CLI harness.
Open sourcekeyword match
Gen-Verse/OpenClaw-RL · Python
Project described as training any agent by talking. Repository topics include GRPO, RLHF, on-policy distillation, skill learning, memory systems, and SGLang, and the homepage links an arXiv paper. It targets OpenClaw and other harnesses.
Open sourcekeyword match
microsoft/skill-recorder · TypeScript
Desktop app that records an on-screen work session and uses the GitHub Copilot SDK to reconstruct it as intent and ordered steps. It then builds a reusable skill or automation for Microsoft Autopilots such as Scout, Copilot Cowork, or Copilot Studio.
Open sourcekeyword match
breaking-brake/cc-wf-studio · TypeScript
VS Code extension for Claude Code workflow automation, tagged for agent skills, MCP tools, slash commands, and sub-agents. The extension is listed on Open VSX.
Open sourcekeyword match
aipoch/open-science · TypeScript
Local-first, model-agnostic desktop app for scientific research and agent workflows. It includes extensible skills, MCP tools and connectors, Python/R execution, and traceable artifacts for reproducible research on macOS, Windows, and Linux.
Open sourcekeyword match
eugeniughelbur/obsidian-second-brain · Python
Persistent memory for Claude Code, Codex, and six other AI agents, stored as plain markdown in an Obsidian vault. Crew is a shared logbook so Claude Code, Codex, Cursor, and Grok Bot can see what each other did. It also describes semantic search over notes.
Open sourcekeyword match
liustack/modlens · TypeScript
A vision plugin for DeepSeek Harness and a bridge that adds vision to text-only coding agents. Pasting an image returns structured JSON evidence for OCR, layout, and semantics. It is listed for Claude Code, Codex, OpenClaw, Hermes, and Pi.
Open sourcekeyword match
jordan-gibbs/hyperresearch · Python
A skill that turns Claude Code or Codex into a deep research agent. It collects, searches, and synthesizes web research into a persistent, searchable wiki, and offers a hosted API and an MCP server.
Open sourcekeyword match
inkeep/open-knowledge · TypeScript
An AI-native markdown IDE and LLM wiki. It includes agent skills for Claude and Codex and is oriented toward knowledge bases, notes, and markdown documentation.
Open sourcekeyword match
haydenschmitty/floorplan · JavaScript
A plugin for Claude Code and Codex that draws an interactive, plain-English map of how an app fits together. It is aimed at codebase visualization and onboarding.
Open sourcekeyword match
zenbu-labs/terminal-browser · TypeScript
A browser that runs inside the terminal, listed as a plugin for Claude Code and Codex. Repository topics also include Claude skills.
Open sourcekeyword match
isjiamu/gzh-design-skill · HTML
Skill for Claude Code, Codex, and Cursor that converts Markdown into HTML meant to be pasted into the WeChat editor. It includes six themes, a theme generator, and two-stage validation.
Open sourcekeyword match
plannotator/effective-html · HTML
Skills for Claude Code and Codex that help agents produce HTML artifacts, including wireframes, interactive prototypes, plans, and diagrams.
Open sourcekeyword match
arjun988/blender-skills · TypeScript
Ninety-four specialist Blender skills for Cursor, Claude Code, Kiro, and Codex. The project describes an MCP-powered pipeline from blockout through engine export.
Open sourcekeyword match
NVIDIA/skills · Python
Agent skills for NVIDIA products that install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end. The repository is Python under Apache-2.0, with docs at docs.nvidia.com/skills.
Open sourcekeyword match
lennney/stop-that-shit · JavaScript
A multi-platform hook and skill guard for AI coding agents in Codex, Claude Code, OpenCode, and Hermes workflows. It targets unrequested hashes, checksums, and task-scope creep. Released as JavaScript under MIT.
Open sourcekeyword match
rebelytics/one-skill-to-rule-them-all · Markdown
A Claude Code meta-skill that turns corrections, judgement calls, and repeated workflows from autonomous or human-led sessions into small skill updates and new skill candidates, each with evidence and a reason. Nothing is applied to a skill until you approve it. Licensed CC BY 4.0.
Open sourcekeyword match
scenario-labs/skills · Python
Skills for coding agents that pick a model, price a job before spending, and keep characters and brands consistent through the Scenario MCP for image, video, audio, and 3D. Also described as expert-team skills that drive Blender, Maya, ZBrush, Unreal, and Unity.
Open sourcekeyword match
Ar9av/obsidian-wiki · Python
Framework for AI agents to build and maintain an Obsidian wiki as a memory system. It targets Claude Code and Codex and is described as agent memory and a knowledge base.
Open sourcekeyword match
agenticnotetaking/arscontexta · Shell
Claude Code plugin that generates an individualized knowledge system from a conversation about how you think and work. The output is a second brain as markdown files the user owns.
Open sourcekeyword match
oil-oil/oil-ui · Python
Skill for Claude Code, Codex, and other AI agents that explores distinct UI directions, compares them side by side, and refines designs against real screenshots.
Open sourcekeyword match
giancarloerra/SocratiCode · TypeScript
Plugin, skill, extension, or MCP for local private codebase intelligence. It provides hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis and call flow, an HTML viewer, and cross-project branch-aware search, plus DB, API, and infra knowledge. A cloud version is in beta.
Open sourcekeyword match
NVIDIA/SkillEvaluator · Python
Multi-tier framework for evaluating AI agent skills and plugins. It includes quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.
Open sourcekeyword match
rpamis/comet · JavaScript
Comet is an agent skill harness for turning ideas into evaluated workflows. It focuses on skill creation, specs, phase-guarded loops, and evals.
Open sourcekeyword match
yaojingang/yao-meta-skill · Python
YAO (Yielding AI Outcomes) is an MIT-licensed system for engineering, evaluation, governance, and portability of reusable agent skills.
Open sourcekeyword match
caru-ini/stack-diagram · TypeScript
Stack Diagram is an agent skill that takes a one-sentence stack description and produces an architecture diagram with official logos. It targets Claude Code, Codex, Cursor, and other agents.
Open sourcekeyword match
antonbabenko/terraform-skill · Unknown
Terraform Skill is an agent skill for Terraform and OpenTofu covering testing, modules, CI/CD, and production patterns. It is published for Claude Code.
Open sourcekeyword match
coldteadotai/pr-lens · TypeScript
PR Lens is an agent skill for understanding code through diagrams, including architecture, data-flow, and sequence diagrams. It targets Claude Code, Codex, and OpenCode.
Open sourcekeyword match
bergside/typeui · TypeScript
TypeUI is a TypeScript CLI that gives coding agents design-system guidance for building UI. It targets Claude Code, Codex and Gemini CLI, and is tagged as an agent skill and Gemini CLI extension.
Open sourcekeyword match
stripe/ai · TypeScript
Stripe's official repository for building AI-powered products and businesses on Stripe. It is tagged for LLM agents, MCP and workflows, and ships a Gemini CLI extension. Documentation is at docs.stripe.com/agents.
Open sourcekeyword match
morganlinton/BeautifulRust · Python
BeautifulRust is a set of agent skills that guide coding agents to write, review, and port idiomatic Rust. It includes a tested Clippy config and works with Claude Code, Codex, Copilot, Cursor, and Gemini CLI.
Open sourcekeyword match
EL4CTEO/blender-skills · Python
Agent skills that encode Blender 5.3 workflows for coding agents, covering modeling, UVs, PBR, baking, rigging, animation, export, and QA. Works with Claude Code, Codex, Gemini CLI, Copilot, and Cursor.
Open sourcekeyword match
a5c-ai/babysitter · JavaScript
Babysitter is a plugin for Claude Code, Codex, Hermes, and Pi that orchestrates agent work through deterministic workflow steps. It targets complex, multi-step agent tasks rather than one-off prompts.
Open sourcekeyword match
activeloopai/hivemind · TypeScript
Hivemind turns agent traces into reusable skills for use across agents, including Claude Code and Codex. The project is framed as an agent memory and skill layer built from those traces.
Open sourcekeyword match
Kaelio/ktx · TypeScript
ktx is an executable context layer for data and analytics agents. It lets Claude Code, Codex, and other agents query analytical databases with company context.
Open sourcekeyword match
vshulcz/deja-vu · Go
Local memory, session search, and cross-agent handoff for coding agents such as Claude Code, Codex, Cursor, OpenCode, and Gemini CLI. It ships as a single Go binary with hooks and an MCP server.
Open sourcekeyword match
hyhmrright/brooks-lint · HTML
brooks-lint provides portable code-quality review skills for Codex, Cursor, Copilot, and other coding agents. It ships six agent skills covering architecture, technical debt, tests, and remediation.
Open sourcekeyword match
jordanrendric/claude-video-vision · TypeScript
A Claude Code plugin that extracts video frames and analyzes audio so Claude can watch and understand videos. It is listed for Claude Code and Gemini CLI and is tagged as an MCP server.
Open sourcekeyword match
hesamsheikh/octogent · TypeScript
A thin orchestration dashboard over Claude Code for managing context, automation, and developer headspace. It targets the Claude Code and Codex harnesses.
Open sourcekeyword match
matlab/simulink-agentic-toolkit · HTML
The Simulink Agentic Toolkit gives an AI agent tools and expertise for Simulink and Model-Based Design. It is a MATLAB project for Claude Code, Codex, and GitHub Copilot, with topics that include agent skills, MCP tools, and a MATLAB MCP server.
Open sourcekeyword match
griffinmartin/opencode-claude-auth · TypeScript
An OpenCode 2 plugin that uses existing Claude Code credentials so no separate login is needed. It is written in TypeScript for the OpenCode and Claude Code harnesses.
Open sourcekeyword match
matlab/matlab-agentic-toolkit · MATLAB
The MATLAB Agentic Toolkit brings MATLAB capabilities to AI agents through agent skills and an MCP server. It targets Claude Code, Codex, and GitHub Copilot for engineering and scientific workflows.
Open sourcekeyword match
conorluddy/ios-simulator-skill · Python
An iOS Simulator skill that lets agents build, run, and interact with apps, and proxies xcodebuild to reduce token use. It works with Claude Code, Codex, and similar agents.
Open sourcekeyword match
reticlehq/reticle · TypeScript
Reticle is an agent skill and MCP server for testing and verifying what agents build. It adds machine-native runtime perception for web and desktop applications and is listed for Claude Code.
Open sourcekeyword match
openqodex/openqodex · TypeScript
Open-source AI code review for coding agents. A separate reviewer checks every change the agent writes before you push, in Claude Code, Codex, Cursor, and Cline. It does not require an account or API key of its own.
Open sourcekeyword match
agentrq/agentrq · Go
Self-hosted realtime conversational task manager for controlling AI agents from mobile, web, or desktop. It is designed to work with your own Claude subscriptions and any harness with ACP support.
Open sourcekeyword match
JayPokale/Chisle · JavaScript
A zero-dependency skill that targets coding-agent token use on three axes: terse prose, YAGNI-first code, and tool-output compression. It supports Claude Code, Pi, Cursor, Codex, Gemini CLI, and four other harnesses, and publishes benchmarks including runs it loses.
Open sourcekeyword match
microsoft/power-platform-skills · JavaScript
A plugin marketplace for GitHub Copilot and other AI agents that provides Power Platform development plugins, including reusable skills, agents, and commands for building and deploying solutions.
Open sourcekeyword match
prompt-security/clawsec · JavaScript
A security skill suite for OpenClaw, Hermes, PicoClaw, and NanoClaw agents and variants. One install covers drift detection for files such as SOUL.md, live security recommendations, automated audits, and skill integrity verification.
Open sourcekeyword match
Paradigm-Study/claude-share · TypeScript
Claude Share is a Claude Code plugin for live multiplayer sessions. Share a link to work together and review the same replies, tools, and previews. It is TypeScript, MIT-licensed, and can be self-hosted.
Open sourcekeyword match
ChatCut-Inc/agent-plugin · JavaScript
ChatCut is a plugin and MCP server for Codex, ChatGPT, Claude Code, Cursor, Grok, Gemini CLI, WorkBuddy, Doubao Work, and Qwen Work. Agents can edit footage by chat, add captions and subtitles, remove silences and filler words, create motion graphics, and export an editable timeline.
Open sourcekeyword match
GaoSSR/best-claude-hud · Rust
A minimal Claude Code statusline HUD implemented in Rust. It runs in the terminal on Linux, macOS, and Windows and is distributed as an npm package.
Open sourcekeyword match
alexeyw/lot-map · TypeScript
lot-map shows a live map beside the chat of what Claude Code is doing. Tool calls, model steps, hooks, skills, and subagents light up as they happen. It is local only and available in 7 languages.
Open sourcekeyword match
unbrowse-ai/unbrowse · Rust
Unbrowse is a Rust project for letting agents use the web without a browser. It is published as plugins for Claude Code, Codex, Gemini CLI, and OpenClaw, and is tagged as an MCP server.
Open sourcekeyword match
fivetaku/fablize · Python
Fablize is a Claude Code plugin that applies completion, evidence, and verification as procedure so Opus follows behavior carried over from Fable. It says it ships only what a Fable-versus-Opus comparison showed was transferable.
Open sourcekeyword match
kingbootoshi/cartographer · TypeScript
A TypeScript Claude Code plugin that maps and documents codebases using parallel AI subagents.
Open sourcekeyword match
23blocks-OS/ai-maestro · TypeScript
An AI agent orchestrator with a skills system for managing Claude Code, Codex, Grok Build, or other agents from one dashboard. It provides memory search, code graph queries, and agent-to-agent messaging, and can move agents between computers and locations.
Open sourcekeyword match
chipfighter/context-attachment-manager · TypeScript
A local plugin for image-heavy chats in Codex, Claude Code, and other agents. Earlier images become short placeholders; the model fetches the original by ID, including after compaction, and the prompt cache keeps working.
Open sourcekeyword match
ReflexioAI/claude-smart · Python
A plugin that turns corrections into preferences, project-specific skills, and shared skills for Claude Code, Codex, and OpenCode.
Open sourcekeyword match
quant-sentiment-ai/claude-equity-research · Python
Claude Code plugin that generates buy/sell recommendations from fundamental analysis, technical indicators, and risk assessment. The repo marks it for educational use and not as financial advice.
Open sourcekeyword match
hellowind777/hello2cc · JavaScript
A native-first Claude Code plugin for third-party models, with silent Agent model injection and output styles. JavaScript, Apache-2.0.
Open sourcekeyword match
aannoo/hcom · Rust
Lets AI agents message, watch, and spawn each other across terminals. Supports Claude Code, Codex, Antigravity CLI, Cursor CLI, OpenCode, Kilo, Pi, and Kimi.
Open sourcekeyword match
Shopify/Shopify-AI-Toolkit · JavaScript
Agent plugins and extensions for CLIs and IDEs, published by Shopify. JavaScript, MIT licensed, and listed as a Gemini CLI extension.
Open sourcekeyword match
docker/skills · Python
A Docker collection of skills that help AI coding agents build, test, debug, and optimize containerized apps with reusable workflows. It is listed for Claude Code, Codex, Cursor, Gemini CLI, Copilot, and Antigravity.
Open sourcekeyword match
coldteadotai/abide · TypeScript
A plugin that makes a coding agent abide by a project's rules. It supports Claude Code, Codex, and OpenCode.
Open sourcekeyword match
shekohex/opencode-pty · TypeScript
An OpenCode plugin for interactive PTY management. It runs background processes, sends input, and reads output with regex filtering.
Open sourcekeyword match
vladikk/modularity · HTML
Claude Code plugin that designs modular systems from functional requirements and reviews existing codebases for modularity problems. Recommendations are based on the Balanced Coupling model.
Open sourcekeyword match
karanb192/claude-code-hooks · JavaScript
Claude Code hooks plus an installable plugin marketplace covering safety, cost, observability, and productivity.
Open sourcekeyword match
ooples/token-optimizer-mcp · JavaScript
Local, MIT-licensed MCP server that compresses tool output, keeps memory across sessions, and paces subscription quotas. Listed for Claude Code, Codex, Copilot, Gemini CLI, and other agents.
Open sourcekeyword match
Hainrixz/the-architect · Unknown
Claude Code plugin that interviews you, designs the architecture, and writes a self-contained blueprint another Claude Code instance builds from. Each build step includes EARS acceptance criteria and a runnable verify command. It covers 14 project shapes, greenfield and brownfield, in English and Spanish.
Open sourcekeyword match
gitroomhq/postiz-agent · TypeScript
Postiz Agents CLI connects Claude, OpenClaw, and similar agents to Postiz so they can schedule social media posts. The repo lists it as a plugin for Claude Code, Gemini CLI, and OpenClaw.
Open sourcekeyword match
oliver-kriska/claude-elixir-phoenix · Python
Claude Code plugin for Elixir, Phoenix, and LiveView with specialist agents, Iron Laws enforcement, and Tidewave MCP integration. It covers planning with research agents, execution with verification, parallel review audits, and saving learnings as reusable knowledge.
Open sourcekeyword match
heardlabs/heard · Python
Open-source Apache 2.0 macOS tool that reads Claude Code and Codex progress aloud. Voice can run locally with Kokoro without an account, or with an ElevenLabs or Speechify key. It speaks a short summary when an agent finishes, fails, or needs approval.
Open sourcekeyword match
Ikalus1988/MisakaNet · Python
MisakaNet serves evidence-graded debugging fix lessons to coding agents through an MCP call, framed as failure memory for reuse of prior fixes. It is listed as a plugin for Claude Code, Codex, OpenCode, and Hermes.
Open sourcekeyword match
stormzhang/token-tracker · Python
Local token tracker for Claude Code and Codex. It adds a status line, a GitHub-style usage heatmap, and multi-model cost analysis.
Open sourcekeyword match
ZaxbyHub/opencode-swarm · TypeScript
OpenCode plugin for architect-centric multi-agent orchestration. It uses hub-and-spoke coordination for specialist consultation, code generation, and QA review.
Open sourcekeyword match
prevalentWare/opencode-goal-plugin · TypeScript
OpenCode plugin that adds Codex-style goal mode, /goal slash commands, and persistent objectives for a coding agent.
Open sourcekeyword match
Innei/ryugi · JavaScript
Artifacts for coding agents, including mockup artboards, design docs, whiteboards, HTML benches, and verify reports. Comments on an artifact are sent back to the agent. Install artifacts alone, or a brainstorm, spec, and TDD workflow, on Claude Code, Codex, and other harnesses.
Open sourcekeyword match
Piebald-AI/claude-code-lsps · JavaScript
A Claude Code plugin marketplace that packages LSP servers for the coding agent.
Open sourcekeyword match
aerovato/operator-memory · TypeScript
A memory and context plugin for coding agents, packaged for Claude Code, Codex, OpenCode, and Kiro.
Open sourcekeyword match
salemalem/npmscan-mcp-plugin · TypeScript
NPMscan is an MCP plugin for Gemini CLI that scans npm packages for supply-chain security issues. It is written in TypeScript and released under the MIT license.
Open sourcekeyword match
cablate/mcp-google-map · TypeScript
MCP server and standalone CLI with 18 Google Maps tools and 3 agent skills for place search, routes, travel planning, and local SEO. Written in TypeScript, MIT licensed, and published on npm.
Open sourcekeyword match
wenlan-app/wenlan · Rust
Open-source studio that gathers notes and memories from AI tools into pages, skills, and rules that stay current and customizable. It includes an MCP server and targets Claude Code, Codex, Cursor, Gemini CLI, Copilot, and Windsurf. Written in Rust under Apache-2.0.
Open sourcekeyword match
fcakyon/labrat · Python
Plugin of PhD research skills for coding agents, covering paper reproduction, experiment design, paper review, and result comparison. Listed for Claude Code, Codex, Cursor, and Gemini CLI.
Open sourcekeyword match
zapier/mcp · Unknown
Official plugin distribution for the hosted Zapier MCP server. Install it in an AI client to connect to thousands of apps. Supports Claude Code, Codex, Cursor, Gemini CLI, Copilot, and Kiro.
Open sourcekeyword match
boshu2/agentops · Go
DevOps discipline for AI coding agents that shapes the work, tracks it as a graph, and has each change judged by a context that did not write it. Plugins target Claude Code, Codex, OpenCode, and Cursor.
Open sourcekeyword match
NahumLitvin/prismantis · TypeScript
A Claude Code mod that renders replies with tables, code, diagrams, charts, and tool rows in 15 themes, with copy buttons. Also listed for Codex and OpenCode.
Open sourcekeyword match
scaccogatto/okf-skills · Python
Toolkit for Claude Code to author, maintain, validate, and visualize Open Knowledge Format bundles. Ships as a plugin, agent skills, and a GitHub Action, with MCP and structured-knowledge topics.
Open sourcekeyword match
prekuter/dryforge · Python
Dryforge is a bounded-autonomy plugin harness for agents, described as taking work from intent to implementation. It is a Python plugin for Claude Code, Codex, GitHub Copilot, and Antigravity.
Open sourcekeyword match
data-goblin/claude-code-filetree · TypeScript
An IDE-style file tree for Claude Code that shows which files the agent reads and edits. The pane includes git status, diffs, content search, file previews, and guarded paths, in the terminal and the Claude Desktop app.
Open sourcekeyword match
Community-Access/accessibility-agents · JavaScript
WCAG 2.2 AA accessibility review for AI coding tools. It provides Agent Skills, an edit gate, and accessibility scanners for Claude Code, GitHub Copilot, Gemini CLI, and Codex.
Open sourcekeyword match
stephenleo/cship · Rust
A customizable statusline for Claude Code with Starship-style TOML config, themeable colours, and Nerd Font glyphs. It includes tunable thresholds for cost, context, and usage.
Open sourcekeyword match
danjdewhurst/story-skills · JavaScript
story-skills provides agent skills for end-to-end story writing in markdown. It is packaged as plugins for Codex and Claude Code and published on npm.
Open sourcekeyword match
seyedehsanhadi/sloptrim · Python
sloptrim is a local detector for AI-writing patterns that scores every prose file an agent saves. It is a Claude Code plugin written with the Python standard library only, with no network access and no model.
Open sourcekeyword match
humanplane/homunculus · Shell
homunculus is a Claude Code plugin that watches how you work, learns your patterns, and evolves itself to help you better. It is implemented in shell.
Open sourcekeyword match
leeguooooo/claude-code-usage-bar · Python
claude-code-usage-bar is a lightweight Claude Code statusLine for 5-hour and 7-day rate-limit usage, reset countdowns, model and context window, and prompt-cache age. It includes 3 styles, 9 themes, and a daemon fast-mode, and is published on PyPI.
Open sourcekeyword match
pegasi-ai/reins · Python
Claude Code and OpenClaw plugin for stopping agents from doing things you did not ask for. Topics cover agent observability, audit trails, human-in-the-loop intervention, and agent security.
Open sourcekeyword match
mcpware/cross-code-organizer · JavaScript
Cross-harness config dashboard for Claude Code, Codex CLI, MCP servers, skills, memories, agents, sessions, security scanning, context budget, and backups. Formerly Claude Code Organizer.
Open sourcekeyword match
yeswehack/claude-kit · Unknown
A Claude Code plugin for writing triager-grade bug bounty reports. It is published by YesWeHack under the GPL-3.0 license.
Open sourcekeyword match
CronusL-1141/AI-company · Python
A Claude Code mod for multi-agent teams. It describes MCP tools, agent templates, lifecycle hooks, pipeline workflows, persistent teams, structured meetings, a task wall, and a React dashboard, with native Claude Code integration rather than LangChain or AutoGen.
Open sourcekeyword match
obra/superpowers-chrome · HTML
A Claude Code plugin for direct Chrome browser control through the DevTools Protocol. The repository describes it as having zero dependencies.
Open sourcekeyword match
referodesign/refero_skill · Python
Research-first design skill for AI agents. It offers 150K+ real app screens and flows through Refero MCP and is packaged for Claude Code, Codex, Cursor, and Gemini CLI.
Open sourcekeyword match
adversa-ai/secureclaw · TypeScript
Security plugin and skill for OpenClaw. The project describes itself as OWASP-aligned and is tagged for agentic AI, LLM security, and the OWASP LLM Top 10.
Open sourcekeyword match
huisezhiyin/sdd-riper · Python
Lightweight AI agent harness for agentic coding. Strong models explore while humans steer with minimal specs, checkpoints, approval, validation, and reverse sync. It targets Claude Code, Cursor, and OpenClaw.
Open sourcekeyword match
hypothesi/mcp-server-tauri · TypeScript
A Model Context Protocol server and plugin for Tauri v2 development. It is also listed as a Gemini CLI extension, with automation and CLI topics.
Open sourcekeyword match
ussumant/llm-wiki-compiler · HTML
Claude Code plugin that compiles markdown knowledge files into a topic-based wiki. It implements Karpathy's LLM Knowledge Base pattern.
Open sourcekeyword match
swiftlysingh/excalidraw-cli · TypeScript
Generates editable Excalidraw diagrams from text or JSON for agents and developer workflows. Listed as a plugin for Claude Code, Codex, and Gemini CLI.
Open sourcekeyword match
Hotakus/opencode-visual-cache · TypeScript
Sidebar plugin for the OpenCode TUI that displays real-time token cache hit rate. Written in TypeScript, MIT-licensed, and published as the npm package opencode-visual-cache.
Open sourcekeyword match
Signet-AI/signetai · TypeScript
Syncs and stores memories, transcripts, institutional knowledge, and secrets across harnesses and models. Ships plugins for Claude Code, Codex, OpenCode, OpenClaw, Hermes, and Pi, and is described as self-hosted.
Open sourcekeyword match
iamumeransari/claude-show-your-work · TypeScript
Claude Code plugin for reviewing agent output in the terminal: show images, play videos, and run visual QA with Playwright recordings and before/after comparisons. Works in terminals that support the kitty graphics protocol on macOS, Linux, and Windows.
Open sourcekeyword match
prime-radiant-inc/greenfield · Unknown
Claude Code plugin that reverse-engineers behavioral specs, test vectors, and acceptance criteria from a codebase. It keeps a provenance trail so a new team can reimplement without inheriting the original internal structure.
Open sourcekeyword match
eclipse-theia/theia · TypeScript
Eclipse Theia is an open-source platform for building custom IDEs and tools for browser and desktop. It includes Theia AI, the vendor-neutral AI harness platform, and powers the AI-native Theia IDE.
Open sourcekeyword match
mozilla/firefox-mcp · TypeScript
Model Context Protocol server that lets AI agents browse the web and debug web pages with Firefox. It is a plugin for Claude Code, Codex, Cursor, Gemini CLI, and Cline.
Open sourcekeyword match
Sunghwan0112/spritecast · Python
Claude Code plugin that generates game sprites at a game's camera angle, drawn in the project's art style. It covers props, 8-direction walking characters, and characters seated on custom chairs with 3D guidance.
Open sourcekeyword match
htdt/godogen · Python
Skills for Claude Code, Codex, and Antigravity to build games and other work that a game engine renders well. Listed engines and libraries include Godot, Bevy, Babylon.js, and Three.js.
Open sourcekeyword match
tractorjuice/arc-kit · JavaScript
Plugin for Claude Code and other AI coding assistants that applies enterprise architecture governance. It includes 76 commands that draft requirements, business cases, and design reviews, with listed support for Codex, OpenCode, Gemini CLI, and GitHub Copilot.
Open sourcekeyword match
Tencent/LoopForge · Go
LoopForge is a self-hosted workflow system for coding-agent delivery. It orchestrates CodeBuddy, Codex, and Claude Code with scripts and human approval gates, and includes local workflows for coding assistants.
Open sourcekeyword match
hridaya423/phonedriver · Rust
MCP server and CLI that lets AI agents see and control Android phones and iPhones. It reads the screen as text and asks before it pays. Works with Claude Code, Codex, Cursor, and other agent harnesses.
Gatheringkeyword match
Oct 8, 2026 · San Francisco, CA
An SF Tech Week session on the auth stack for AI agents — delegated permissions, machine identities and scoped access for agents acting in production systems. Registration via Luma.
Gatheringkeyword match
Nov 5–6, 2026 · San Francisco, CA
A two-day developer summit at the SF Marriott Marquis on building agents and apps on Box ('the filesystem for agents and apps'), with sessions alongside Browserbase, Temporal and Daytona.