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
Mem0/mem0 · Python
Mem0 extracts, stores and retrieves salient facts from conversations and documents — a managed memory layer with an open-source core that has become a default choice for agent memory.
Open sourcekeyword match
Nous Research/hermes-agent · TypeScript
Nous Research's self-improving personal agent: a learning loop turns experience into reusable skills and builds a model of the user across sessions. It runs from a terminal UI, a desktop app or chat apps such as Telegram, Discord and Slack, all attached to one gateway that owns every session, on anything from a $5 VPS to serverless backends.
Startupkeyword match
Stateful agents with memory, from the team behind MemGPT. · Berkeley, CA
Letta (formerly MemGPT, out of UC Berkeley) builds an agent server with built-in memory, context management and state — letting agents persist, learn and be edited like files rather than living in a chat window.
Startupkeyword match
The memory layer for AI apps and agents. · San Francisco, CA
Mem0 (from the EmbedChain team) provides a managed + open-source memory layer that extracts, stores and retrieves user and entity memories across sessions — a standard building block for personalization.
Startupkeyword match
Long-term memory for agents, built on temporal knowledge graphs. · San Francisco, CA
Zep maintains durable, time-aware agent memory via its open-source Graphiti engine — facts, relationships and their history — so conversations and tasks can span sessions.
Startupkeyword match
User modeling and psychology for agent memory. · New York, NY
Honcho is a user-context and memory server that models what each user knows and wants, so agents can personalize without teams hand-rolling their own user-modeling stack.
Startupkeyword match
The programming language for agentic software. · United States
Agno (formerly Phidata) builds a high-performance open-source agent runtime — memory, knowledge, storage and monitoring built in — aiming to be the substrate beneath agentic applications rather than just a framework.
Startupkeyword match
Open AI lab behind the Hermes models and Hermes Agent. · Remote-first
Nous Research, known for open-weight Hermes LLMs and decentralized training, ships hermes-agent — a self-improving, always-on personal agent that turns experience into reusable skills and keeps a persistent user model, lean enough to run on a $5 VPS.
Startupkeyword match
Open-source AI agents that work for you.
TinyHumans builds a family of open-source agents: OpenHuman, a local-first Rust harness with private lifelong memory; OpenCompany, an agent 'hive mind' that thinks as one team; and Medulla, a terminal that runs Claude Code, Codex and OpenCode side by side.
Startupkeyword match
A complete coding-agent harness — confidence-gated routing, institutional memory.
Grist (grist.lol) is a complete coding-agent harness: every task is routed to the cheapest capable model rung by confidence gates, every verified change is remembered as institutional memory, and inference is billed to your own provider key. npm install -g grist-ai.
Startupkeyword match
Raven — the harness of harnesses, built for recursive self-improvement.
EverMind AI builds Raven, an open-source, trusted, persistent and self-evolving multi-agent ecosystem designed for recursive self-improvement (RSI), alongside memory-sparse-attention research for scaling end-to-end memory to 100M tokens.
Startupkeyword match
Memory and context engine for AI, offered as an API, plugins and a local binary.
Supermemory builds a memory and context layer for AI applications and agents. It extracts facts from conversations, handles temporal changes, contradictions and automatic forgetting, maintains user profiles (about 50 ms per call), and combines RAG with memory in hybrid search. It offers connectors for Google Drive, Gmail, Notion, OneDrive and GitHub, and multimodal extractors. It ships plugins and an MCP server that give Claude Code, Cursor, Codex and OpenCode persistent memory, plus a developer API and a self-hostable single binary. TechCrunch reported a $2.6M seed round in October 2025 for founder Dhravya Shah.
Startupkeyword match
Agent-native memory infrastructure that turns agent execution into persistent state.
Memori Labs builds Memori, an LLM-agnostic memory layer that turns agent execution traces and conversations into structured, persistent state. The open-source SDKs (pip `memori`, npm `@memorilabs/memori`) register an existing LLM client and attribute memories to entities and processes so later runs recall them automatically; a Memori Cloud service and a gateway on the inference path are offered commercially. The site emphasizes governance (access-controlled memory pools, audit logs) and deployment across managed cloud, single-tenant cloud, VPC and on-prem. The repo is Apache-2.0.
Startupkeyword match
Enterprise AI coding platform and context engine, now part of Tricentis.
Tabnine is an AI coding platform built for secure, context-aware enterprise software development, founded and led by CEO Dror Weiss. Its Enterprise Context Engine maps an organization's code, documentation, tickets and APIs into a continuously refreshed knowledge structure, supporting dependency and impact analysis, governance checks and shared memory for multi-agent workflows, and can run on-premises, in a private cloud or fully air-gapped. On July 30, 2026, testing company Tricentis announced it had acquired Tabnine and will integrate the context engine into its agentic quality engineering platform; tabnine.com now redirects to Tricentis.
Startupkeyword match
A context graph of your codebase and SDLC for AI agents.
Potpie turns a codebase and its software-delivery lifecycle into a living context graph for AI agents, indexing code structure, decisions, source history, team knowledge and workflows so agents can answer questions, plan changes, debug failures and write code with project-specific context. The open-source CLI (Apache-2.0, about 5.8k GitHub stars) runs a setup wizard that provisions a local daemon and agent skills and plugs into the user's chosen coding harness, such as OpenAI Codex. Its enterprise offering runs agents inside the customer's VPC and adds spec-driven development; Potpie says it was one of 20 picks for Google's 2026 Accelerator.
Startupkeyword match
The context layer for agentic software development. · Vancouver, BC
Unblocked merges code, conversations, issues, docs, product data and production systems into one knowledge graph and resolves conflicts between sources using recency, authority and proximity, so agents know what to trust. Its Organizational Memory mines team conventions from PR review feedback and history, results are permission-scoped with source links, and it is accessed via MCP (Cursor, Claude Code, Copilot), CLI, Slack, web and API. The Vancouver company, led by founder and CEO Dennis Pilarinos, raised a $20M USD Series A led by B Capital in May 2025.
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
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 Cloud in one line of code · San Francisco, CA
Langbase is a serverless platform for building, deploying and scaling AI agents, which are exposed as APIs (pipes) and can connect to 600+ LLMs, tools and MCP servers. It provides a managed memory/RAG service, and multi-step multi-agent workflows with retries, timeouts and step-level traces. It also offers Studio for versioning agents, plus tracing, cost tracking and evals. Its site also promotes Command Code, a coding agent.
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
Context layer for AI agents
Graphlit positions itself as the context layer for AI agents, supplying them with context from connected data sources. It maintains an open-source MIT-licensed MCP server in TypeScript.
Startupkeyword match
Kanban board that hands tasks to your agent harness with persistent context
AgentKanban is a kanban board for planning work and handing tasks off to AI agents, keeping agent chat activity attached to each task. Claude Code, Codex, Cursor or any MCP-compatible agent can load a task by ID, resume it with context and update the board. It also ships a VS Code extension.
Startupkeyword match
A learned memory layer for enterprise agents that prepares memories ahead of time to cut token costs.
Engram builds a learned memory layer for enterprise AI agents. Its CEO, Dan Biderman, says the approach can "prepare memories ahead of time instead of pasting them on the fly", reducing what agents must load into context. It came out of stealth in June 2026 with $98M from investors including General Catalyst, Kleiner Perkins, Sequoia and Factory.
Startupkeyword match
The hivemind for human–agent teams: shared team memory that gives coding agents team context. · Seattle, WA
SageOx builds team memory for human and AI work, describing itself as "the hivemind for human–agent teams". Its tools give coding agents the context a team has built up. The Seattle company raised a $15M seed round led by Canaan in May 2026.
Startupkeyword match
Turns expert workflow knowledge into lasting memory for AI agents.
Interloom captures how experts actually work and turns that workflow knowledge into lasting memory that AI agents can use. It announced a $16.5M seed round led by DN Capital in March 2026.
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
The powerful agent for work, built on a shared company brain.
Hyper launched on Hacker News in June 2026 as a shared "company brain" to power agentic development, arguing that "the bottleneck now is that these smart-enough models often lack information about your company". Its site now presents Hyper as "the powerful agent for work". It is part of Y Combinator's Spring 2026 batch.
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
Background agents for engineering teams · Sofia, Bulgaria
Felan runs background AI agents for software engineering teams. They pick up the recurring work nobody should have to watch, like dependency updates, test fixes, flaky CI and small refactors. Agents start from events, schedules or a person, run on their own, and hand back a result your team reviews. They run in Felan's managed cloud or on your own infrastructure. What makes it different: it's built to keep agent costs low and visible. - No markup on tokens. Use your own API keys or subscriptions, or buy credits at provider rates. - No lock-in. Works with any popular model or provider, including local and private models, so you can use cheap models for simple tasks and top models for hard ones. - Felan Code, our open-source coding agent, is tuned to use fewer tokens without lowering quality. It's the same agent on your laptop and on the platform. - Per-task cost visibility. You see what every agent and task costs. Felan sits next to the local agents your developers already use. It doesn't replace them.
Open sourcekeyword match
Agno/agno · Python
Agno (formerly Phidata) markets itself as 'the programming language for agentic software' — a fast agent runtime with built-in memory, knowledge, storage and a monitoring UI, aiming to be the production substrate beneath frameworks.
Open sourcekeyword match
Letta/letta · Python
Letta (the company behind MemGPT) builds an agent server where agents have persistent memory, self-editing state and tool use — the reference open-source take on memory as a first-class part of the harness.
Open sourcekeyword match
Zep/graphiti · Python
Graphiti (by Zep) builds dynamically updating, time-aware knowledge graphs from unstructured data — powering agentic memory that knows not just facts but when they were true.
Open sourcekeyword match
MemTensor/MemOS · TypeScript
MemOS treats memory as an OS-level resource — scheduling, storing and evolving different memory types (parametric, activation, plaintext) with hybrid retrieval. A research-born take on industrializing agent memory.
Open sourcekeyword match
Topoteretes/cognee · Python
cognee turns documents, conversations and APIs into knowledge graphs and vector stores that agents can query — an open-source 'memory engine' positioned between RAG and long-term memory.
Open sourcekeyword match
Headroom Labs/headroom · Python
Headroom compresses tool outputs, logs, files and RAG chunks before they reach the LLM — 20% fewer tokens for coding agents and 60–95% for other workloads. Context engineering as infrastructure: keeping the window usable as harnesses grow.
Open sourcekeyword match
Vectorize/hindsight · Python
Hindsight is an open-source memory framework for agents that learns what to remember — extracting, scoring and retrieving from experience to improve over time, rather than storing everything and hoping retrieval sorts it out.
Open sourcekeyword match
Volcengine (ByteDance)/OpenViking · Python
OpenViking unifies agent memory, knowledge RAG and skills into a single self-evolving 'context database'. Volcengine's answer to the memory question: one store that feeds agents everything they know and learn.
Open sourcekeyword match
thedotmack/claude-mem · TypeScript
claude-mem runs a second agent beside your coding agent that records what it does and compresses it into observations; later sessions start with a short index and pull in details only when needed. It records sessions for Claude Code, Codex, Cursor, OpenCode, Antigravity, Pi, DeepSeek Harness, OpenClaw and others, while Copilot CLI, Goose, Roo Code, Warp and Zed get memory search only. It also includes My Work, a viewer of your requests and their status.
Open sourcekeyword match
TinyHumans/openhuman · Rust
OpenHuman is TinyHumans' local-first, Rust-written agent harness: it builds a private memory of your life, runs agents and workflows for you, and does the deep research you'd never get to — online or offline, on hardware you own.
Open sourcekeyword match
EverMind AI/Raven · Python
Raven is EverMind AI's 'harness of harnesses': a trusted, persistent, self-evolving multi-agent ecosystem designed for recursive self-improvement — agents that modify their own harness under governance rather than by fiat.
Open sourcekeyword match
Letta/agent-file · Python
Agent File (.af) is Letta's open format for serializing stateful AI agents with persistent memory — portable agent state you can move between harnesses. A step toward agents as files rather than walled gardens.
Open sourcekeyword match
Affaan Mustafa/ECC · JavaScript
ECC is an MIT-licensed set of agents, skills, hooks, rules, memory and continuous-learning workflows that it installs into coding-agent harnesses. Its loop is plan, test, implement, review, verify, remember, improve. It works best with Claude Code and has native plugin paths for Codex and Qoder. For Cursor, OpenCode, Gemini, Zed, Copilot and others it offers adapters with fewer capabilities. The README lists 71 agents and 311 skills, plus AgentShield, a security scanner for agent configurations. ecc.tools also sells a paid GitHub App tier at $19 per seat per month and an enterprise tier.
Open sourcekeyword match
Open GSD/gsd-core · JavaScript
GSD Core is the successor to Get Shit Done (gsd-build/get-shit-done), whose repository has been archived with a pointer to open-gsd/gsd-core. It is an MIT-licensed context-engineering and spec-driven development framework aimed at 'context rot'. It drives coding agents through a five-step loop for each phase: discuss, plan, execute, verify and ship. Plans run in parallel waves, and each executor starts with a fresh context. An npx installer configures it for Claude Code, OpenCode, Codex, Copilot, Cursor, Windsurf, Kimi CLI, Antigravity CLI and others.
Open sourcekeyword match
MemPalace/mempalace · Python
MemPalace is an MIT-licensed, local-first memory system for AI agents. It stores conversation history verbatim, without summarising or extracting, and retrieves it with semantic search over a structured index. People and projects become 'wings', topics become 'rooms' and original content sits in 'drawers'. ChromaDB is the default store, with a pluggable backend interface and an optional native Rust engine. Agent skills install it and configure MCP for coding agents such as Claude Code. The README reports 96.6% R@5 on LongMemEval with zero API calls and commits the benchmark results to the repo.
Open sourcekeyword match
HKUDS (Data Intelligence Lab @ HKU)/nanobot · Python
nanobot, from the HKU Data Intelligence Lab in Hong Kong, is an MIT-licensed, ultra-lightweight, self-hosted personal agent framework in Python. It runs in a browser WebUI, the terminal or chat apps: Telegram, Discord, Slack, WeChat, Feishu, Teams, email, Mattermost and Linear. Built-in tools cover shell, web search and fetch, Office files, MCP, cron and multi-agent delegation. Session history and long-term memory ('Dream') persist across sessions, and it supports long-horizon goals and scheduled automations. A Python SDK and an OpenAI-compatible API are included, and it works with hosted or local models.
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
zhayujie/CowAgent · Python
CowAgent, previously named chatgpt-on-wechat, is an MIT-licensed personal AI assistant that calls itself a complete agent harness. Messages arrive through channels such as the web and major IM platforms. An agent core then plans and reasons over memory, a knowledge base, tools and skills, and replies through the same channel. It can control the computer and external services, create and run skills, form multi-agent teams and evolve its long-term memory. It runs 24/7 on a PC or server, deploys via a one-line installer or Docker, has a web console, and is managed with the cow CLI.
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
Rohit Ghumare/agentmemory · TypeScript
agentmemory captures coding-agent sessions through native hooks and plugins, with secret scrubbing and offline replay. It makes decisions and fixes searchable so agents can recall them later and hand sessions off to another agent. It supports Claude Code, GitHub Copilot CLI, Cursor, Gemini CLI, Codex CLI, Hermes, OpenClaw, Pi, oh-my-pi, OpenCode, DeepSeek Harness and any MCP client. Keyless mode uses BM25 search, and local or remote embeddings add semantic recall and graph matching. It runs a local API and a live viewer for browsing, editing, exporting and forgetting memories. The README says it extends Karpathy's LLM Wiki pattern.
Open sourcekeyword match
Gas Town Hall/beads · Go
Beads (`bd`) is a distributed, dependency-aware graph issue tracker built for AI coding agents and powered by the Dolt version-controlled SQL database. It replaces markdown plans with a task graph so agents can work on long-horizon tasks: `bd ready` surfaces claimable work, hash-based IDs avoid merge collisions across agents and branches, and semantic compaction summarizes old closed tasks to save context. `bd init` and `bd setup` install guidance and hooks for Claude Code, Codex, Cursor and Factory Droid, and issues can be synced between machines and agents via Dolt remotes.
Open sourcekeyword match
Mindfold/Trellis · TypeScript
Trellis is a project layer that works across multiple coding agents and IDEs (e.g. Cursor, OpenCode, Codex), installed via npm and initialized per repo. It runs a four-phase loop with auto-invoked skills and sub-agents: brainstorm a PRD one question at a time, implement with curated context injected, check the diff against specs plus lint, type-check and tests, and finish by promoting learnings into versioned `.trellis/spec/` files. It adds scoped specs, task boundaries, workflow gates and per-developer workspace journals, and `trellis ablate` temporarily removes its files for comparison. Licensed AGPL-3.0.
Open sourcekeyword match
NevaMind AI/memU · Python
memU is a lightweight memory system that gives users a shared LLM wiki across sessions, agents and devices; its core memory logic is about 500 lines. Host adapters connect it to Codex, Claude Code, Cursor, OpenClaw, Hermes, pi and others. A scheduled bridging task captures new session history, and the agent itself decides whether to create or patch reusable Markdown skills, which memU embeds and returns on similar future tasks; the memory service makes no LLM calls itself. It can be used via a hosted API key at memu.so or self-hosted.
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
EvoMap/evolver · JavaScript
Evolver is EvoMap's self-evolution engine for AI agents, based on its GEP (Genome Evolution Protocol), which records evolution as auditable Genes, Capsules and Events. EvoMap's site describes GEP as letting agents share, validate and inherit capabilities across models. A linked arXiv paper (2604.15097) argues compact 'Gene' representations beat documentation-style skill packages for accumulating experience. Released open source in Feb 2026 (MIT, then GPL-3.0); the README says future releases will move to source-available, while published versions keep their original licenses.
Open sourcekeyword match
Osaurus/osaurus · Swift
Osaurus is an open-source AI harness for macOS built in native Swift for Apple Silicon. It sits between the user and any local or cloud model and keeps agents, memory, tools and identity on the user's machine. Each agent has its own prompts, memory and theme; tools and skills are selected via RAG, and the project lists persistent memory, autonomous execution and cryptographic identity among its features. It works fully offline with local models (an optional build bundles a ~4 GB model) and requires macOS 15.5+. Its site notes a Windows public beta.
Open sourcekeyword match
Builder Methods/agent-os · Shell
Agent OS is a lightweight system from Brian Casel's Builder Methods for keeping coding agents aligned with how a team already builds. It extracts patterns and conventions from an existing codebase into documented standards, indexes them, injects the relevant standards based on what is being built, and helps shape better specs before implementation. It works alongside Claude Code, Cursor, Antigravity and other AI tools, independent of language or framework.
Open sourcekeyword match
ByteRover/byterover-cli · TypeScript
ByteRover CLI (`brv`, formerly Cipher) gives AI coding agents persistent, structured memory. Developers curate project knowledge into a context tree stored as markdown under `.brv/context-tree/`, with git-like versioning (branch, commit, merge, push/pull), a review workflow for curate operations, a web dashboard and optional cloud sync for teams. It supports many LLM providers. The GitHub repository was archived in June 2026 under the Elastic License 2.0, though the docs and npm package remained live afterward.
Open sourcekeyword match
Letta/letta-code · TypeScript
Letta Code is a stateful agent harness from Letta for agents with memory, identity and experience over time. Agents learn by rewriting their own memory blocks, skills and prompts. Context is tracked in git through MemFS. It offers message search, subagents, hooks, permission modes and self-managed crons and heartbeats. Users can reach the same agent from a local CLI, the browser at chat.letta.com, or Slack, Telegram and Discord. It installs via npm, uv or pipx.
Open sourcekeyword match
RedPlanet/core · TypeScript
CORE describes itself as an open-source, self-hosted personal AI OS that is always on. It indexes email, meetings, GitHub, Linear, Slack and assistant conversations into a temporal knowledge graph so each task starts with prior context loaded. Work is organized as one-shot or recurring tasks that can spawn coding sessions (for example running Claude Code and opening a PR), drive a browser or run terminal commands. It can be reached through a daily scratchpad, voice, and WhatsApp, Slack or Telegram. The code is AGPL-3.0 licensed (copyright Poozle Inc.).
Open sourcekeyword match
Ghostwright/phantom · TypeScript
Phantom is an open-source AI co-worker built on the Claude Agent SDK that runs on its own dedicated machine, where it installs software, spins up databases, builds tools and keeps persistent memory across sessions. It ships with Slack, Telegram, email and webhook channels plus a web chat, has its own email identity, exposes an MCP server and supports secure credential collection. Although Anthropic is the default, it supports seven providers including Z.AI, OpenRouter, Ollama, vLLM and LiteLLM, configured via YAML.
Open sourcekeyword match
NextLevelBuilder/goclaw · Go
GoClaw is a multi-agent AI gateway shipped as a single static Go binary, originally inspired by the OpenClaw architecture. It runs an eight-stage agent pipeline (context, history, prompt, think, act, observe, memory, summarize), three-tier memory with a knowledge graph, agent teams with shared task boards and delegation, 20+ LLM providers and seven messaging channels. A multi-tenant PostgreSQL mode adds per-user workspaces, RBAC and encrypted keys; a desktop 'Lite' edition runs on SQLite. Note: licensed CC BY-NC 4.0 (non-commercial).
Open sourcekeyword match
SwarmClaw/swarmclaw · TypeScript
SwarmClaw is an open-source, self-hosted AI agent runtime and multi-agent framework for running agent swarms and orchestrators. It provides heartbeats, cron schedules and webhook triggers, delegation between agents or to CLI backends (Claude Code, Codex, OpenCode, Gemini, Goose and others), agent memory, runtime skills, a Kanban task board with audit trail, and connectors for Discord, Slack, Telegram and WhatsApp. It supports 23+ LLM providers and can sit on top of OpenClaw gateways and Hermes agents. Distributed as a desktop app, Docker Compose stack or from source.
Open sourcekeyword match
Nimbalyst/nimbalyst · TypeScript
Nimbalyst (the successor to the Crystal parallel-worktree app) is an MIT-licensed desktop workspace for macOS, Windows and Linux, with iOS/Android companions, for running multiple coding agents in parallel and editing their work visually across markdown, mockups, diagrams, docs and tasks. It works with existing Claude Code or Codex subscriptions or API keys. A separate Nimbalyst Wiki plugin lets MCP-compatible agents maintain a shared, human-editable wiki of decisions and open questions, with a paid Wiki Teams plan (free in beta).
Open sourcekeyword match
Potpie AI/potpie · Python
Potpie builds a graph-based representation of large codebases and connects it with context from tools such as GitHub, Sentry, Jira and Notion or Confluence, so AI agents have the context they need to work in complex engineering environments. The open-source repository describes itself as a 'Context Graph for AI Native SDLC'. Potpie AI, founded by Aditi Kothari and Dhiren Mathur, launched publicly in January 2025 and raised a $2.2M pre-seed led by Emergent Ventures in February 2026.
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
OthmanAdi/planning-with-files · Python
Manus-style persistent file-based planning for AI coding agents, with crash-proof markdown plans, session recovery after /clear and compaction, and per-turn re-injection to counter context rot. It installs from npm, the Claude Code plugin marketplace or npx skills, and supports Codex, Cursor, OpenCode and 60+ other agents.
Open sourcekeyword match
parcadei/Continuous-Claude-v3 · Python
Context management for Claude Code: hooks keep state across sessions using ledgers and handoffs. It also runs MCP tools without polluting the context, and orchestrates agents in isolated context windows.
Open sourcekeyword match
langchain-ai/langmem · Python
LangMem helps agents learn and adapt from their interactions over time. It extracts important information from conversations, refines agent prompts and keeps long-term memory. It offers functional primitives that work with any storage system and integrates natively with LangGraph's storage layer.
Open sourcekeyword match
memodb-io/memobase · Python
Memobase is a user-profile-based long-term memory system for AI chatbot applications. It persists user context across sessions so agents can recall users over time. Apache-2.0 licensed Python project with a hosted offering at memobase.io.
Open sourcekeyword match
Mirix-AI/MIRIX · Python
MIRIX is a multi-agent personal assistant that tracks on-screen activity and consolidates captured data into structured memories. These memories form a knowledge base that the assistant uses to answer user questions.
Open sourcekeyword match
aws/bedrock-agentcore-sdk-python · Python
Python SDK for turning any AI agent into a production-ready application. Gives framework-agnostic primitives for runtime, memory, authentication and tools, running on AWS-managed infrastructure (Amazon Bedrock AgentCore).
Open sourcekeyword match
compozy/compozy · Go
CompozyOS is a local runtime, a daemon with a CLI, HTTP/SSE and a web UI. It turns agent CLIs such as Claude Code, Codex, Gemini CLI and Cursor into a team that splits work, hands off tasks, runs scheduled jobs and loops, and shares one project memory. The runtime enforces task leases, permissions and approvals. It is currently in beta.
Open sourcekeyword match
Graphify-Labs/graphify · Python
Graphify turns a codebase and its docs, SQL schemas, configs and PDFs into a knowledge graph that agents can query. It installs from pip and adds a /graphify SKILL.md to the agent's skills folder, and it hooks into the agent's tool calls in Claude Code, Codex and others.
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
tamaratran/fast-jev-compaction · TypeScript
A Claude Code plugin and npm library that replaces the compaction summary. It scores each tool call and result, drops or truncates the stale ones, and keeps everything else word for word.
Open sourcekeyword match
Tarquinen/opencode-dynamic-context-pruning · TypeScript
An OpenCode plugin that prunes conversation context dynamically to cut token usage.
Open sourcekeyword match
supermemoryai/opencode-supermemory · TypeScript
The official Supermemory plugin that gives OpenCode persistent memory.
Open sourcekeyword match
tickernelz/opencode-mem · TypeScript
An OpenCode plugin that gives coding agents persistent memory backed by a local vector database.
Open sourcekeyword match
zilliztech/memsearch · Python
A persistent memory layer shared across AI agents such as Claude Code, Codex, OpenCode, OpenClaw and Pi, backed by Markdown and Milvus.
Open sourcekeyword match
memorax-ai/memorax-code · JavaScript
A memory plugin for AI coding that keeps engineering experience, repo knowledge and your working style as memory for future tasks.
Open sourcekeyword match
rohitg00/pro-workflow · JavaScript
A Claude Code workflow layer that learns from your corrections, with self-correcting memory, context engineering, parallel worktrees, agent teams and 17 skills.
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
SethGammon/Citadel · JavaScript
Operating layer for Claude Code and OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry and parallel agent fleets.
Open sourcekeyword match
obra/episodic-memory · TypeScript
Claude Code plugin that indexes past conversations so the agent can search and recall them.
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
infiniflow/ragflow · Go
RAGFlow is an open-source RAG engine described as an agent-native database and context infrastructure. Repository topics cover agentic retrieval, context management, and retrieval harnesses.
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
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
EverMind-AI/EverOS · Python
EverOS is a portable memory layer for AI agents. It is local-first and Markdown-native, user-owned, and described as self-evolving across apps, tools, and workflows.
Open sourcekeyword match
TencentCloud/Octop · Python
Octop is a self-hosted AI assistant for multi-user, multi-agent use. Repository topics include agentic AI, local-first deployment, and long-term memory.
Open sourcekeyword match
trailhq/Trail-Code · TypeScript
Trail-Code is a shared memory for coding agents on a team. It gives Claude Code, Cursor, and Codex a map of the code and past decisions so they can continue from earlier work. Topics include MCP, a code graph, and context engineering.
Open sourcekeyword match
xerrors/Yuxi · Python
Yuxi is a self-hosted, multi-tenant knowledge agent platform. It combines RAG, knowledge graphs, multi-agent workflows, MCP and skills, sandboxing, and permission management.
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
kungfu-systems/kungfu · C++
Keeps the same work moving across Codex, Claude, OpenCode, and your own execution surface instead of handing work off between agents. Topics include agent orchestration and agent memory.
Open sourcekeyword match
code-yeongyu/lazycodex · TypeScript
Agent harness for complex codebases that covers project memory, planning, execution, and verified completion inside Codex. Repository topics also reference Claude Code and orchestration.
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
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
cortexkit/magic-context · TypeScript
magic-context is a TypeScript project in CortexKit for agent memory and context management aimed at coding agents. Repository topics include context engineering, cache-aware context handling, LangChain, and OpenCode.
Open sourcekeyword match
ShenSeanChen/waku-agent · Python
Waku Agent is a local-first AI agent harness that includes the loop, memory, and eval in code intended to stay legible as it grows. It is written in Python and released under the MIT license.
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
aoci-spec/aoci-code · Go
aoci-code is a local-first MCP server and CLI in Go that keeps a persistent, Git-versioned map of a codebase and database schema. Coding agents such as Claude Code, Codex, Cursor, and opencode read that index for long-term context, memory, and code intelligence.
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
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
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
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
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
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
BayramAnnakov/claude-reflect · Python
A self-learning skill for Claude Code that records corrections, positive feedback, and preferences, then syncs them to CLAUDE.md and AGENTS.md.
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
sno-ai/sno-station-skills · Shell
Open-source skills for Claude Code, Codex, Cursor, and Hermes Agent. They cover review by a different agent, a handover before a usage limit stops the work, treating done as proven by a real run, and a nightly loop that learns from your own sessions.
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
kitfunso/hippo-memory · TypeScript
Hippo writes what you teach a coding agent into a store in your repo, and other agents read that same store. It targets Claude Code, Codex, OpenCode, Cursor, and OpenClaw, and lists local-first SQLite storage plus an MCP server.
Open sourcekeyword match
raiyanyahya/recall · Python
Recall gives Claude Code and OpenCode durable memory that works entirely offline, so project context does not have to be re-explained every session.
Open sourcekeyword match
KimGLee/Cambium · Python
Governance standard and reference toolset for LLM-maintained knowledge corpora. Repository topics include auditability, human-in-the-loop, policy-as-code, MCP, and Claude Code plugins.
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
MaxFreedomPollard/Compartment · Python
Compartment is encrypted, fully offline agent memory with a one-click install and a GUI that includes a memory map. It is listed as an MCP plugin for Claude Code, Gemini CLI, OpenClaw, and Hermes, for local memory creation, storage, and retrieval.
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
aerovato/operator-memory · TypeScript
A memory and context plugin for coding agents, packaged for Claude Code, Codex, OpenCode, and Kiro.
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
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
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
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
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.
Gatheringkeyword match
Nov 21, 2026 · Online
A 4.5-hour hands-on online workshop (11:00–15:30 ET) on building agents that keep memory over time and manage context, with memory bootstrapped from Oracle AI Database.
Gatheringkeyword match
Nov 14, 2026 · Toronto, Canada
A one-day Toronto hackathon building durable agentic systems with MongoDB Atlas, Vector Search and agentic memory. Up to $21K CAD in cash plus $6K in LangSmith credits.