#ai-agents

AI agent & MCP trust registry — independent, evidence-based trust scores for 1.3K+ open-source AI agents and MCP servers. Runtime-trust calibrated (MCP, dependencies, provenance drift), with side-by-side comparison and embeddable live badges. Ranked by verifiable signals, not hype.

Self-hosted AI agent harness in a single Go binary — writes, sandbox-tests and repairs its own tools, and lets Claude Code, Codex and any MCP client build and share them.

An autonomous coding agent that lives inside your own GitHub. You file an issue, it opens a pull request, and a human decides whether to merge.

Go library for driving AI coding CLIs in headless mode.

Lightweight HTML-to-Markdown parser for AI agent workflows — Python CLI and API around a fast Go engine, available on PyPI.

Record a browser workflow once, get a deterministic MCP tool your AI agent can call. Zero tokens at runtime. Postman for AI agents.

A framework for Forward Deployed Engineers: from problem statement to a deployable AI project — every decision traced to a fact, every fact to a source.

Run AI-generated JavaScript from Python, securely, in a sandbox: real V8 in a supervised, OS-sandboxed worker process (Seatbelt, Landlock, seccomp), with your Python functions as the only way out.

Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. ｜ 覆盖主流期刊的 Claude Code/Codex 期刊技能包，从选题、识别策略到表格规范与审稿回复全流程，助你快速发论文。

A local-first multi-agent coding harness that connects model providers and ACP agents, binds them to specialized roles, and coordinates them in a shared session.

Open-source governed-sandbox control plane for any workload — per-run identity, brokered credentials, layered egress, approvals, and an append-only audit. Coding agents are the flagship use. Apache-2.0, self-hosted.

Fast cold-boot MicroVM sandboxes for AI agents on cocoon

Real-time dashboard for monitoring Claude Code, Codex, and other AI coding agents—with animated 3D robots, live terminals, tool activity, prompt queues, and session resume.

Deep research skill for pi — structured search, reflection, and analysis.

AI-native web fetch engine for LLM agents — browser impersonation, semantic DOM pipeline, MCP server. CGO-free Go.

A self-improving reflection / skill-creation agent on LangGraph — the LangStage reference agent

Find out what your coding agents already know. Docmancer indexes the memory, rules, and instructions Claude Code, Codex, Cursor, and Gemini wrote on your machine, then carries the durable parts to every agent. It is local-first and under MIT license.

Keep Claude Code and Codex aligned with task requirements through intent proof, drift checks, visible run state, and evidence-based verification.

The neutral meter for AI agent work: neither side keeps the count.

Keeping your agents out of trouble with sandboxed coding agent automation

Harness-agnostic toolkit for AI coding agents: detect the harness (Claude, Codex, Cursor, Cline, Gemini, Aider...) and run a pure policy core. One Bun-native package.

Drop it into your repo and let an AI Senior reviewer go through every PR — inline comments, severity-coded findings, and a general summary, all configurable per project and tech stack. Supports OpenAI, Anthropic, Gemini, and Ollama. Auto-detects your stack (NestJS, Next.js, React, TypeScript, Node, Flutter, Laravel) and applies built-in rules for

The scenario is the asset; runners are swappable. Define mobile app journeys once, run them through any agent, device, or profiler, and preserve stable evidence that tells agents and humans whether behavior improved, regressed, or can't be trusted yet.

Node.js client for the OpenClaw Gateway WebSocket protocol

Go/Golang multi-agent LLM framework — ReAct loops, parallel tool calls, streaming, sub-agents, and pluggable Anthropic / OpenAI / Gemini providers.

Cross-harness AI skill portability CLI. Author an agent skill once, sync it into Claude Code, Cursor, Copilot, Codex, OpenCode & 45+ AI coding agents. Safety scanner, content-hash drift detection. A package manager / dotfiles for AI coding agent skills.

Docs your AI agent can write and your CI can check. Markdown + typed YAML blocks for diagrams, API docs, ADRs, and slides, rendered by code, never drawn by the model.

The React framework for building agents into real apps — one definition serves humans (streamed HTML, zero client JS) and agents (markdown, JSON, MCP), nothing duplicated. Web-standards core, deploys to Cloudflare Workers.

Kura — the knowledgebase for humans and agents. Agent-native docs infrastructure, built on June.

Open-source, self-hostable server and runtime core for Run402 — backend infrastructure for AI agents. Postgres/PostgREST with RLS, storage, routing, functions and portable project archives. Apache-2.0.