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
promptfoo/promptfoo · TypeScript
promptfoo is an open-source testing framework for LLM apps: eval matrices, assertions, RAG metrics and an AI red-teaming scanner for vulnerabilities. Config-in-YAML, CI-friendly.
Startupkeyword match
Red-teaming and robustness for AI agents. · New York, NY
Haize Labs stress-tests agents with automated adversarial attacks — prompt injection, tool misuse, unsafe actions — and ships an SDK for continuous safety evaluation in CI.
Startupkeyword match
Automated evaluation and guardrails for LLM systems. · San Francisco, CA
Patronus AI scores outputs against policy and business criteria in CI and production, catching regressions before users do — 'unit tests for AI'.
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
AI gateway with guardrails for production agents. · Bengaluru, India
Portkey builds an AI gateway that routes across 1,600+ models with integrated guardrails — caching, fallbacks, load balancing, rate limiting and observability — the control plane between a harness and every model provider. Strong presence in the APAC market.
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
Agent access governance — what agents can reach. · Tel Aviv, Israel
Apono built just-in-time access governance for cloud and data infrastructure, then extended it to AI agents — granting scoped, auditable permissions to agent identities instead of static credentials. Acquired by 1Password in July 2026 to anchor its agentic access-control line.
Startupkeyword match
The execution layer that 'parents' AI agents. · San Francisco, CA
Runta builds an agent execution layer with sandboxes, spending caps and audit trails — a 'parenting' layer for agents that directly addresses the containment failures exposed by prompt-injection incidents. a16z called it 'core systems software rebuilt for agents'; $20M seed at a $100M+ valuation (Jul 2026).
Startupkeyword match
Plano: AI-native proxy and data plane for agentic apps.
Katanemo develops Plano, an open-source (Apache-2.0) AI-native proxy server and data plane for agentic applications, built on Envoy and written in Rust. Plano moves delivery concerns out of application code into an out-of-process data plane: low-latency routing and orchestration between agents, LLM routing by model name, alias or preferences, zero-code capture of 'Agentic Signals' plus OpenTelemetry traces and metrics, and filter chains for jailbreak protection, moderation and memory hooks. It works with any language or agent framework.
Startupkeyword match
Open-source evals, red teaming and test generation for agentic systems.
Giskard builds an open-source (Apache-2.0) Python library for testing and evaluating agentic systems, alongside a commercial AI red-teaming and LLM security platform. Giskard v3 is a modular rewrite for dynamic, multi-turn agent testing: Giskard Checks for evals from simple assertions to LLM-as-judge, and giskard-scan for vulnerability scanning and RAG evaluation, built on giskard-core, giskard-llm and giskard-agents. It can wrap an LLM, a black-box agent or a multi-step pipeline. v2 remains available but is no longer actively maintained.
Startupkeyword match
Open-source platform for evaluating, tracing and improving AI agents.
Future AGI builds an open-source, self-hostable platform for shipping AI agents that covers the lifecycle in one feedback loop: simulations of edge cases before launch, evaluations, tracing and observability in production, real-time guardrails, an LLM gateway, datasets and optimization. It positions itself as a replacement for stitching together separate tools for evals, observability, guardrails and simulation. The platform is Apache 2.0 licensed, with a free cloud tier alongside self-hosting.
Startupkeyword match
Security workers and guardrails for code, agents and infrastructure. · San Francisco, CA
Superagent, a YC W24 company based in San Francisco, builds what it calls an autonomous security factory. Its products include PR Security, which checks code, contributor, workflow and supply-chain risk before merge; scheduled dependency updates; Red Team adversarial testing; Context Guardrails, which score what agents consume before they trust it; and Runtime Guardrails, which monitor or block risky agent actions where they run. Findings become reviewed remediation PRs, and it can hand work to coding agents such as Cursor and Devin. Its open-source repo (MIT) targets prompt injection, data leaks and harmful outputs.
Startupkeyword match
Background software-engineering agents in governed, VPC-deployable cloud environments.
Ona, the company formerly known as Gitpod (Gitpod GmbH), runs AI engineering agents in full cloud development environments that can be deployed in the customer's VPC. Background agents take a task and return a pull request; automations trigger agent fleets from PRs, schedules or webhooks for work like CVE remediation and code migration. Runtime controls include audit trails, scoped credentials and kernel-level policy enforcement, and teams can run Ona, Codex and other agents under shared policies. OpenAI announced on June 11, 2026 that it is acquiring Ona, with the team joining Codex.
Startupkeyword match
Agentic software delivery governed by approval thresholds and audit logs.
Revolte describes itself as an agentic platform for software engineering in which AI agents handle development, testing, deployment and production operations while engineers approve outcomes. Approval thresholds can be set per workflow, team or risk level so consequential decisions route to a human first, and every agent action is logged for audit. It integrates with existing stacks such as AWS, Google Cloud, Datadog, Jira, Linear and ServiceNow. The site footer names Poddle.io Ltd; performance figures on the site are vendor-reported.
Startupkeyword match
A context- and intent-aware AI software factory with guardrailed agents.
Opsera sells an AI-driven software delivery platform; its Forge product, launched in April 2026, is a governed 'software factory' that converts intent into machine-readable specifications before code is written, reverse-engineers legacy COBOL, .NET and Java systems into specs, and keeps a persistent context layer to reduce drift. Humans supervise agents through auditable work orders, agentic actions are mapped to corporate policies, and a ForgeScore scorecard rates output across eight dimensions. Opsera also offers IDE AppSec agents, AI-spend analytics and policy-as-code DevOps.
Startupkeyword match
A self-improving software factory with evaluator and healer meta-agents.
Autoheal runs always-on cloud agents for SDLC work such as incident response, vulnerability remediation, release readiness and AI coding cost control. Supervisory Evaluator agents score worker output using signals like review comments, CI failures and linked incidents, while Healer agents propose changes to prompts, skills, tools or model choice, test them against historical benchmarks and submit them for engineer approval in Git. Each run gets a fresh sandbox in the customer's cloud with policy checks on every tool call, per-agent budgets and audit trails. It raised a $7.9M seed led by Innovation Endeavors (Sept 2026).
Startupkeyword match
Build your own AI software factory.
Port is a platform for building, governing and operating an agentic software development lifecycle. It discovers agents, MCP connectors and skills across an organization so teams can enforce their standards. Agents handle tasks such as provisioning infrastructure, resolving tickets and fixing pipeline failures, under governance controls with humans kept in the loop.
Startupkeyword match
Your developers have guardrails. Your AI doesn't.
Coder provides self-hosted AI development infrastructure that lets developers use any model or agent while giving enterprises governance and control. Coder Agents is a native coding agent that works with any model on infrastructure you control. Coder AI Governance centralizes model access, enforces policy-controlled environments and keeps audit trails. Coder Workspaces are standardized, self-hosted environments shared by developers and agents.
Startupkeyword match
Autonomous Operations Factory for DevOps, SRE and platform engineering
StackGen offers an 'Autonomous Operations Factory' in which AI agents carry infrastructure work from request to production, with human approval on key actions. Its Aiden agents cover SRE (alert triage, root cause, remediation), InfraOps (Terraform/OpenTofu generation, policy checks, drift remediation, MCP integration with coding tools), Observability and DevOps request triage. Shipyard provides ephemeral environments for developers and their agents.
Startupkeyword match
Pulumi's AI infrastructure agent
Pulumi Neo is an AI agent that provisions, governs and optimizes cloud infrastructure, covering provisioning, updates, debugging and cost analysis. It enforces existing Pulumi policies (RBAC, compliance, security standards) and supports configurable autonomy with human-in-the-loop approval workflows. Every action is previewed, logged and reversible.
Startupkeyword match
AI writes code. Riza runs it.
Riza is an API for running code written by an LLM in isolation from production systems and secrets, with per-run control over environment variables and network access. The site says execution starts in under 10ms with no sandbox startup. It offers Python, TypeScript and Go SDKs, lets agents write reusable tools, and can be self-hosted on Kubernetes.
Startupkeyword match
On-demand isolated Linux microVMs for running untrusted or AI-generated code
Vercel Sandbox runs arbitrary code in on-demand Firecracker microVMs, each with its own kernel, controlled through an SDK or CLI. Claude, Codex and OpenCode come preinstalled in the base image, so coding agents can run inside a sandbox. It has egress policies with credential injection on outbound requests, snapshots that can start parallel instances, sessions up to 24 hours on paid plans, and persistent Vercel Drives.
Startupkeyword match
Test, Monitor and Self Improve voice agents
Cekura is an automated QA platform for voice and chat AI agents. It runs synthetic conversations before an agent goes live, monitors production calls for drift, and can block deploys when release test suites fail. It also does adversarial red-teaming for jailbreaks and data leaks, and suggests prompt fixes for issues it reproduces in simulation.
Startupkeyword match
AI quality platform to standardize evals and observability across the organization
Confident AI is an AI quality platform for enterprise teams to standardize evals and observability. It builds and maintains the open-source DeepEval evaluation framework and DeepTeam red-teaming framework. For agents it tests tool selection, arguments and full trajectories, and simulates multi-turn conversations. It blocks releases that fail evals or red-team checks and offers an MCP server and agent skills.
Startupkeyword match
AI governance for everyone
Arthur offers one control plane that brings together security, finance and the teams shipping AI. It measures, monitors and governs enterprise AI at scale.
Startupkeyword match
Customer and Agentic Identity Platform
Descope is an External IAM platform for building identity journeys. It covers users, business customers, partners, AI agents and MCP servers.
Startupkeyword match
Runtime auth for agents
Keycard provides runtime authorization for AI agents. Each agent gets its own identity, authority to act, and access to resources under the owner's policy.
Startupkeyword match
Ship AI agents faster and more securely
Auth0, part of Okta, offers identity tooling to help developers ship AI agents faster and more securely. The solution page is aimed at moving identity out of the developer's way while building agents.
Startupkeyword match
Identity Control Plane for AI Agents
Aembit provides runtime IAM for AI agents and workloads. It enforces access policies, keeps downstream credentials out of agents, audits access, and can revoke access with a kill switch.
Startupkeyword match
Identity Security for AI Agents & NHIs
Astrix gives visibility and control over AI agents and non-human identities. It secures agent identities with governance, least-privilege access and full audit trails.
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
MCP & LLM Gateway for the Agentic Enterprise
Mintive, formerly MintMCP, is an MCP and LLM gateway. It gives every agent its own identity and governs access to models and tools by role.
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
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 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
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
AI agent security and governance
Zenity is an AI security platform that lets organizations decide what their AI agents can and cannot do. It evaluates every agent action in real time and steers it.
Startupkeyword match
Agent security and governance platform
Noma offers a unified agent control plane to secure agents on SaaS platforms, endpoints and cloud. Capabilities include agent runtime security, MCP security, agentic identity, AI asset discovery and AI supply chain security.
Startupkeyword match
Securing the agentic workforce
Pillar Security provides AI discovery and posture management, AI red teaming, runtime protection, and compliance and monitoring for AI applications and agents. It publishes the SAIL framework, a practical guide to securing AI agents.
Startupkeyword match
Secure AI adoption at enterprise scale
Lasso is an AI security platform covering AI discovery and inventory, AI agent security, AI governance and AI usage control. Its use cases include AI agent governance, AI gateway security, MCP and prompt injection, and AI coding assistants. It has announced CPU-based guardrails.
Startupkeyword match
Agentic AI Security for Every Agent
Straiker gives security teams visibility and control across AI agents in the enterprise. Discover AI maps agents, MCP servers and agentic workflows; Ascend AI adversarially tests agents for prompt injection and tool misuse; Defend AI provides runtime detection and blocking of threats to agents.
Startupkeyword match
Secure your AI
Operant AI offers real-time discovery, detection and defense for AI, agents and MCP. Products include Agent Protector, an MCP Gateway with registries and allow/deny lists, a Semantic Firewall that allows/blocks/redacts agent actions, and an Endpoint Protector that monitors coding agents such as Claude Code and Cursor on employee devices.
Startupkeyword match
The AI Reliability Platform
Guardrails AI provides a guardrails framework for building, governing and scaling production GenAI with any LLM and deployment environment. It offers runtime guardrails that block bad outputs, a Guardrails Hub of validators, and tooling to generate eval datasets that surface agent failures. The open-source guardrails library is Apache-2.0 licensed Python.
Startupkeyword match
Discover, secure, govern, and optimize every AI agent.
Airia is an enterprise AI security and governance platform that discovers the models, agents, tools and MCP servers a company uses, including unapproved ones. It lets teams build and run agents across models and frameworks, and enforces agent actions at runtime by allowing, blocking, requiring approval, redacting context or logging before a tool call runs.
Startupkeyword match
GenAI and agent security, from SentinelOne
Prompt Security, now branded 'Prompt Security from SentinelOne', provides AI security with guardrails for sensitive data, secrets and prompt injection. It publishes open-source tools including ClawSec (securing agent skills for OpenClaw, NanoClaw and Hermes agents), OneClaw (tracking OpenClaw deployments) and ps-fuzz (testing system prompt resilience).
Startupkeyword match
Run coding agents without babysitting them
MartinLoop is a runtime layer that wraps AI coding agents such as Claude Code, Codex and Gemini CLI. It lets teams hand agents larger software jobs with spend limits, required checks before results are accepted, and a record of each run.
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
A rootless Linux sandbox with gVisor support for running agents safely.
Drop is an open-source, rootless Linux sandbox with gVisor support, built to run coding agents and other untrusted processes without giving them the host. It launched with a Show HN in September 2026 that drew 193 points and 63 comments.
Startupkeyword match
An inline firewall for AI agents and the skills, plugins and MCP servers they use.
AIR builds what it calls an inline firewall for AI agents and the skills, plugins and MCP servers they rely on, sitting between agents and their add-ons to stop malicious behaviour. It came out of stealth on 1 September 2026 with $50M led by Sequoia and Greenoaks.
Startupkeyword match
Agentic AI runtime security: detects threats and enforces policy on enterprise agents in real time.
Eve Security protects enterprise AI agents at runtime, detecting threats and enforcing policies across platforms such as Databricks, Copilot Studio, AgentCore, Bedrock and Glean. It raised a $4.5M seed round led by Run Ventures in September 2026, bringing its seed total to $7.5M.
Startupkeyword match
Privileged access management for AI agents, with per-end-user identity instead of one shared key.
Alter is a credential proxy that gives multi-user agents per-end-user identity and access control. Its founders describe the problem as agents that connect "with one shared API key, so the agent can do anything that the key can do." The site now presents Alter as privileged access management for AI agents. Y Combinator S25.
Startupkeyword match
An AI security and control platform for devices, with an open-source MCP scanner.
Traceforce launched on Hacker News in July 2026 to give companies visibility over the AI apps on their devices and the MCP connections they make. Its site now reads "AI Security & Control Platform for Devices" and offers an open-source MCP scanner. Y Combinator S26.
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
UK AI Safety Institute/inspect_ai · Python
Inspect is the UK AI Safety Institute's open-source framework for large-scale model evaluations — tasks, solvers, scorers and tool sandboxes. The serious-science end of agent evals.
Open sourcekeyword match
QM (yc-software)/open-multi-agent · TypeScript
Open Multi-Agent is the open-source runtime behind QM: a self-hosted TypeScript agent runtime with durable approvals and verifiable run records — 'own it, approve it, audit it' — built for multiplayer agent work.
Open sourcekeyword match
AIMing Lab/AutoHarness · Python
AutoHarness (AIMing Lab) wraps any LLM client in ~2 lines for automated harness engineering: a 6–14 step pipeline, YAML constitution, risk-pattern matching, session persistence with cost tracking and multi-agent profiles. Governance-first, from academia.
Open sourcekeyword match
Electric Capital/quest · TypeScript
Quest is Electric Capital's open-source, self-hosted, safety-focused AI workbench — a harness built around permissioning and trust for agents doing real work. Early-stage (Sep 2026) but backed by a firm that funds much of open-source infrastructure.
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
NVIDIA/NemoClaw · TypeScript
NemoClaw is an open-source reference stack from NVIDIA for running supported AI agents more safely inside NVIDIA OpenShell sandboxes. It provides guided onboarding, managed inference, network policy, managed integrations, OpenShell-backed state persistence and lifecycle operations through the NemoClaw CLI. Supported agents are OpenClaw (the default), Hermes and LangChain Deep Agents Code; an express installer targets DGX and WSL hosts. The project describes itself as alpha, with maintainers reviewing issues and PRs on a best-effort basis.
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
NEAR AI/ironclaw · Rust
IronClaw is an open-source personal agent OS from NEAR AI, written in Rust, aimed at routine tasks such as email triage, meeting prep and deployment monitoring. Its security model runs untrusted tools in WebAssembly containers with capability-based permissions, keeps credentials in an encrypted vault injected only at the host boundary for approved endpoints, scans outbound traffic for leaked secrets and allowlists network access. Data is stored locally and encrypted; hosted instances can run in trusted execution environments on NEAR AI Cloud. It is model-agnostic (Anthropic, OpenAI, Ollama) and installs via a guided `ironclaw onboard` setup.
Open sourcekeyword match
Omnigent/omnigent · Python
Omnigent is an open-source meta-harness: a common orchestration layer over Claude Code, Codex, Cursor, OpenCode, Goose, Antigravity, GitHub Copilot, Devin, Kiro, Qwen Code, Kimi Code, Grok Build, Hermes, Pi and custom YAML-defined agents. Users can swap or combine harnesses without rewriting, have one agent review another's work, and continue sessions across terminal, browser, phone or a macOS desktop app. Sessions can run in disposable cloud sandboxes (Modal, Daytona, E2B, Kubernetes, Databricks and others) or on any machine over SSH, automations can start on a schedule or from Jira, Slack, GitHub, Linear or PagerDuty events, and policies govern agent behaviour. It works with API keys, Claude/ChatGPT subscriptions or compatible gateways.
Open sourcekeyword match
FailproofAI (ExosphereHost Inc)/failproofai · TypeScript
Failproof AI provides observability and enforcement for the harnesses agents run in. It hooks 12 harnesses, ten coding CLIs such as Claude Code and Codex plus the Hermes and OpenClaw chat/assistant gateways, capturing every run into one session history and blocking dangerous tool calls before they execute using 40 built-in policies. Pre-execution blocking is verified on all twelve and turn-end gates on eight. It runs locally (npm i -g failproofai); custom agents can report via a Python SDK. MIT-licensed, copyright ExosphereHost Inc.
Open sourcekeyword match
Microsoft/agent-governance-toolkit · Python
Microsoft's Agent Governance Toolkit is a public-preview library adding policy enforcement, agent identity, execution sandboxing and SRE-style reliability engineering to autonomous agents, installable with one pip install and framework-agnostic. It targets three questions: is an action allowed, which agent performed it, and can it be proven afterwards via tamper-evident decision records. The project argues prompt-level safety is not a control surface and claims coverage of 10/10 of the OWASP Agentic Top 10. Breaking changes are possible before GA.
Open sourcekeyword match
nolabs/nono · Rust
nono is an agent runtime security tool built on kernel-enforced sandboxing. It runs each tool in its own ephemeral sandbox with explicit file, network, environment and credential permissions, keeps API keys outside the agent's sandbox through proxy-based injection, filters network access by domain and API rule, verifies skills and instruction files with Sigstore, and keeps a tamper-evident audit log with file rollback. It is a single unprivileged binary for macOS, Linux and WSL2 and works with Claude Code, Codex, OpenClaw, Hermes and custom agents.
Open sourcekeyword match
OneCLI/onecli · TypeScript
OneCLI is an open-source platform for running AI agents as a team. It started as a Rust credential vault for agents such as Hermes, OpenClaw and NanoClaw. Version 2 provisions one agent per employee from the company identity provider. Each agent runs in an isolated sandbox whose only exit is a gateway that injects credentials and enforces a single team policy. It supports deterministic human-in-the-loop approvals in chat, shared team-level connections and platform-kept memory. It can be self-hosted, including via Helm, or used through the hosted onecli.sh.
Open sourcekeyword match
OpenLIT/openlit · TypeScript
OpenLIT is an Apache-2.0 platform that describes itself as built for agent harness engineering. It provides OpenTelemetry-native tracing of LLM calls, tool calls, MCP requests, retrieval and agent steps; evaluations (LLM-as-judge, programmatic and human feedback) with CI gates; runtime guardrails against prompt injection and restricted topics; a prompt hub, rule engine and secrets vault; model comparison; and cost and GPU monitoring. The self-hosted edition is free; an Enterprise Edition exists, and OpenLIT Cloud was not generally available as of this check.
Open sourcekeyword match
Infisical/agent-vault · Go
Agent Vault is an open-source credential broker from Infisical that sits between agents and the APIs they call. Agents route HTTPS traffic through it via HTTPS_PROXY. The vault terminates TLS with a locally trusted CA, strips any credentials the agent sent, injects the stored credential, and opens a verified connection upstream. This covers APIs, CLIs, SDKs and MCP tools alike, with egress filtering and request logging. Infisical announced it as a research preview on April 22, 2026, for Claude Code, OpenClaw, Hermes and custom harnesses, and recommends its commercial Infisical Agent Vault for production.
Open sourcekeyword match
Emcie/parlant · Python
Parlant is an Apache-2.0 Python platform for customer-facing chat agents in support, sales and lead capture. Since version 4 you describe how the agent should behave and your coding agent (such as Claude Code) implements it as policies, customer variables and tools. Parlant includes a chat widget, human handoff, testing with simulated customers, and a Dashboard with a matching CLI for sessions, reasoning and per-turn model costs. You bring your own model provider, and managed hosting is offered for a flat monthly fee.
Open sourcekeyword match
NVIDIA/OpenShell · Rust
OpenShell is NVIDIA's runtime for running autonomous agents with access to files, packages, APIs and credentials without unrestricted access to data, secrets or network. Each agent runs in an isolated sandbox where kernel-level controls confine file access and system calls and every network connection passes a policy check; agents never see real credentials. Policy changes are checked with formal verification before approval. It includes a gateway control plane, Kubernetes deployment via Helm, SDKs and agent skills.
Open sourcekeyword match
agentgateway/agentgateway · Rust
Agentgateway is a Rust proxy built on AI-native protocols (MCP and A2A) that adds security, observability and governance to agent traffic. It works as an LLM gateway with a unified OpenAI-compatible API, budgets, load balancing and failover; an MCP gateway with tool federation, multiple transports, OpenAPI integration and OAuth; and an A2A gateway. It also offers Kubernetes inference routing, layered guardrails, JWT/OAuth auth, CEL-based RBAC, rate limiting and OpenTelemetry metrics. Its site lists contributors including Solo.io, Microsoft, AWS and Cisco.
Open sourcekeyword match
qhkm/zeptoclaw · Rust
ZeptoClaw is a small, security-focused personal AI assistant runtime packaged as one Rust binary (around 6MB) for running agents locally, at the edge or on a VPS. It bundles tools, long-term memory, channels (Telegram, Slack, Discord, WhatsApp and more), 18 LLM providers with retry and fallback, agent swarms that delegate to sub-agents, a plugin system, cost tracking and token budgets. Its README positions it against OpenClaw-ecosystem security incidents and highlights container isolation across six runtimes, a tool approval gate and prompt-injection detection.
Open sourcekeyword match
disler/claude-code-hooks-mastery · Python
A reference repo showing how to use Claude Code hooks for deterministic or non-deterministic control over Claude Code's behavior. It covers hook lifecycle and payloads, error codes and flow control, sub-agents, a team-based validation system, output styles and custom status lines, all built from UV single-file scripts.
Open sourcekeyword match
openai/codex-action · JavaScript
OpenAI's GitHub Action runs Codex (codex exec) from a GitHub Actions workflow and keeps tight control over the privileges Codex gets. It installs the Codex CLI and configures it with a secure proxy to the Responses API. Users supply an OpenAI or Azure OpenAI key as a secret. The README includes an example of building your own pull request review bot.
Open sourcekeyword match
eqtylab/cupcake · Rust
Cupcake is a native policy-enforcement layer for AI coding agents, built on OPA/Rego. It is developed by EQTY Lab.
Open sourcekeyword match
nizos/tdd-guard · TypeScript
TDD Guard enforces test-driven development in Claude Code automatically, through Claude Code hooks.
Open sourcekeyword match
vndee/llm-sandbox · Python
Lightweight and portable sandbox runtime and code interpreter, as a Python library, for safely running LLM-generated code.
Open sourcekeyword match
NVIDIA-NeMo/Guardrails · Python
NeMo Guardrails is NVIDIA's open-source toolkit for adding programmable guardrails to LLM-based conversational systems.
Open sourcekeyword match
meta-llama/PurpleLlama · Python
PurpleLlama is Meta's set of tools to assess and improve LLM security. The repo contains LlamaFirewall, the Llama Guard safeguards, Prompt Guard (protection against malicious prompts), Code Shield and the CybersecurityBenchmarks (CyberSecEval).
Open sourcekeyword match
NVIDIA/garak · Python
garak is NVIDIA's open-source LLM vulnerability scanner. It probes LLM systems for weaknesses such as jailbreaks, prompt injection and data leakage.
Open sourcekeyword match
snyk/agent-scan · Python
Snyk Agent Scan is an open-source security scanner for AI agents, MCP servers and agent skills. The repo describes itself as 'Security scanner for AI agents, MCP servers and agent skills.'
Open sourcekeyword match
sipyourdrink-ltd/bernstein · Python
Bernstein is an open-source governance layer for AI coding agents. It runs CLI agents in parallel git worktrees and merges only diffs that pass lint, type and test gates. A deterministic scheduler decides what runs, with no model in that loop. It enforces policy as code and keeps an HMAC-chained audit log and Ed25519-signed run receipts. The site cites 40+ agent adapters, including Claude Code, Codex and Gemini CLI, and says it is beta software built by one maintainer.
Open sourcekeyword match
yeameen/claude-code-review-council · See repository
A Claude Code plugin that runs seven reviewers in parallel on the same diff: Codex CLI, Gemini via the Antigravity CLI, and five Claude specialist subagents (security, performance, logic, regression, robustness). A synthesis step de-duplicates findings, verifies each against the actual code, tags severity P0-P3 and surfaces disagreements before any fixes are applied.
Open sourcekeyword match
superhq-ai/superhq · Rust
A Rust/GPUI desktop app for macOS that runs multiple AI coding agents (Claude Code, OpenAI Codex, Pi) in isolated sandbox VMs with full terminal access. Agents never see the real API keys: an auth gateway on the host injects credentials into outgoing requests. The README describes it as very early alpha.
Open sourcekeyword match
dtormoen/tsk-tsk · Rust
Delegates development tasks to YOLO-mode Claude Code or Codex agents running in parallel in filesystem- and network-isolated Docker or Podman containers. It auto-detects the toolchain, builds container images, copies the repo without gitignored files, and enforces a domain allowlist through a proxy sidecar. Agent branches are fetched back to the repo for review.
Open sourcekeyword match
cloudflare/security-audit-skill · JavaScript
Cloudflare's official coding-agent skill for structured security audits. It runs in phases: recon, hunting, then validation by a separate checker, so the agent that finds an issue is not the one that confirms it. Findings come out machine-readable. Install it with npx skills.
Open sourcekeyword match
tech-leads-club/agent-skills · TypeScript
A secure, validated skill registry for professional coding agents such as Claude Code, Cursor, Copilot, Antigravity and Windsurf.
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
Dicklesworthstone/destructive_command_guard · Rust
Rust hook with 50+ security packs, heredoc/inline-script scanning, CI scan mode and explain mode; works with Claude Code, Codex, Gemini, Copilot, Cursor and more. MIT-licensed, with an extra rider covering OpenAI and Anthropic.
Open sourcekeyword match
trailofbits/skills · Python
Trail of Bits skills for security research, vulnerability detection and audit workflows.
Open sourcekeyword match
kenryu42/cc-safety-net · TypeScript
Guard that runs before an agent's tool calls and blocks destructive git and filesystem commands and attempts to read sensitive files, across many harnesses.
Open sourcekeyword match
gemini-cli-extensions/security · TypeScript
Google's security extension for Gemini CLI that finds vulnerabilities in code changes and pull requests.
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
msoedov/agentic_security · Python
Agentic Security is a Python vulnerability scanner and red-teaming kit for agentic LLMs. It is released under the Apache-2.0 license.
Open sourcekeyword match
Azure/agent-landing-zone · Python
Landing zone for AI agent applications on Azure. It can deploy the infrastructure, the agent app, or both, using Microsoft Foundry and Microsoft Agent Framework, with Zero-Trust networking, observability, and infrastructure as code. MIT licensed.
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
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
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
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
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
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
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
karanb192/claude-code-hooks · JavaScript
Claude Code hooks plus an installable plugin marketplace covering safety, cost, observability, and productivity.
Open sourcekeyword match
me2resh/apexyard · Shell
Claude Code skill for governing agent-built code before it ships to production. Repository topics include hooks, skills, code review, multi-agent workflows, and SDLC.
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
SponsioLabs/Sponsio · Python
Open-source project described as deterministic safety solutions for probabilistic AI agents. Topics include guardrails, a policy engine, intent verification, runtime safety, and prompt injection. Packaged as a skill for OpenClaw.
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
hi0001234d/nexpath · TypeScript
A local-first AI coding workflow that checks for missing tests and safety checks across Claude Code, Cursor, Windsurf, Replit, Lovable, and Bolt.new. It is written in TypeScript and licensed Apache-2.0.
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.
Gatheringkeyword match
Oct 6, 2026 · 220 Montgomery St, San Francisco, CA
KALW Public Media hosts a San Francisco panel on AI agents taking actions developers didn't anticipate — the goals, tools, permissions and environments humans set for them. A rare public-media treatment of harness-level safety questions.
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 4, 2026 · London, UK
A Claude Community hackathon at One Canada Square, Canary Wharf: teams get 30 minutes to plan and 2 hours to build a Claude-powered solution to a randomly drawn cybersecurity topic, then present.
Gatheringkeyword match
Nov 11, 2026 · Online
A virtual summit on securing AI coding agents: security requirements, attacking AI-generated code, controlling Claude Code and MCP workflows, and approval gates (from 09:00 ET).
Gatheringkeyword match
Dec 4, 2026 · Online
A three-hour online workshop (09:00–12:00 ET) that takes a refund agent from prototype to production: it reproduces prompt injection, duplicate payments and runaway retries, then applies eval gates, guardrails, tracing and rollback.
Gatheringkeyword match
Oct 29, 2026 · San Francisco, CA
An evening event (17:00–19:30 PT) at Cloudflare SF, 101 Townsend St, on Zero Trust strategies for securing AI models, data and autonomous agents, plus networking. Pitched at a general security audience.
Gatheringkeyword match
Nov 3, 2026 · San Francisco, CA
A developer night at Humanmade, 655 Bryant St, on moving AI agents from prototype to production on Azure: identity, data authorisation and observability with Microsoft Foundry and Elastic, plus an agent-governance workshop. Register on aicamp.ai.
Gatheringkeyword match
Nov 9–10, 2026 · Online
A free two-day virtual conference on safety, security and governance for autonomous agents: sandboxing, prompt-injection defence and running agents at scale, with 5 hands-on tutorials.
Gatheringkeyword match
Dec 15–16, 2026 · Jersey City, NJ
A practitioner AI engineering conference at The Westin Jersey City Newport focused on production agents: agent identity and authorisation (1Password keynote), guardrails on ops agents and eval loops for agentic systems.