The directory for AI agents,
MCP servers & .cursorrules.
Curated open-source tools. Compare frameworks, find alternatives, copy install commands. Updated daily.
Editor's picks
Picked each day from the tools we have reviewed by hand. Selection is based on real data (stars gained in the last 7 days, recent updates); the reason is taken from our own review. Open a card to read it in full.
One desktop agent that runs Claude Code and Codex with shared memory and skills
Why: Reuses a Claude Code or Codex plan you already pay for, so you get a desktop agent without a second model bill.
Gained about 4.1k stars in the last 7 days (3.3k → 7.4k); last updated 10-27
Anthropic's role-based plugins for Claude Cowork
Why: Ready-made starting points for many business roles, each bundling skills, connectors, commands and sub-agents.
Gained about 1.9k stars in the last 7 days (31.5k → 33.4k); last updated 10-27
Agent meta-harness for Claude Code and Codex swarms
Why: Multi-agent coordination and cross-session memory without changing how you use Claude Code day to day.
Gained about 1.4k stars in the last 7 days (78.4k → 79.8k); last updated 10-27
Give a coding agent a local video editor that checks its own output
Why: The probe-edit-verify workflow makes the agent check its own output instead of guessing FFmpeg flags and hoping.
Gained about 1.1k stars in the last 7 days (2.0k → 3.1k); last updated 10-26
Hosted MCP gateway to thousands of ready-made Apify scrapers
Why: Access to a very large catalogue of ready-made scrapers instead of a single tool.
Gained about 900 stars in the last 7 days (12.6k → 13.5k); last updated 10-27
An operating layer for Hermes Agent that adds workflows, model routing and honest evidence records without replacing it
Why: Adds structured workflows to Hermes while keeping Hermes and its native skills in place.
Gained about 800 stars in the last 7 days (3.6k → 4.4k); last updated 10-27
Keep raw tool output out of your agent's context window
Why: Large context savings on tool-heavy sessions by keeping raw output in a sandbox.
Gained about 700 stars in the last 7 days (31.8k → 32.5k); last updated 10-27
An open-source desktop office suite that edits real .docx, .xlsx and .pptx files with an AI whose changes you can review
Why: AI changes are reviewable as tracked changes and diffs, with per-turn rollback.
Gained about 600 stars in the last 7 days (10.5k → 11.1k); last updated 10-27
Best Tools by Use Case
Hand-picked open-source tools grouped by task, comparing stars, licence, 12-week commit activity and install commands side by side.
Best Open-Source Multi-Agent Frameworks in Python & .NET (2026)
Side-by-side comparison of open-source multi-agent and agentic frameworks: CrewAI, Pydantic AI, Google ADK, Microsoft Agent Framework, AgentScope, MetaGPT, and AutoGen.
Best Self-Hosted AI Workflow Automation & Durable Execution Tools (2026)
Compare self-hosted workflow automation builders and durable execution engines for AI agents: n8n, Activepieces, Temporal, Conductor, AutoKitteh, and RuleGo.
Best Open-Source RAG Platforms & Deep Research Agents (2026)
Compare open-source RAG knowledge-base engines and autonomous deep research agents: RAGFlow, MaxKB, GPT Researcher, DeerFlow, MiroThinker, and code-graph-rag.
Best SDKs & Frameworks for Building MCP Servers (2026)
Compare the main ways to build or expose a Model Context Protocol (MCP) server: FastMCP, the official MCP Python SDK, FastAPI-MCP, Grafbase, GitHub MCP Server, and AWS MCP Servers.
Best MCP Servers for Databases: Postgres, MySQL, MongoDB (2026)
Compare open-source MCP servers that let AI assistants query PostgreSQL, MySQL, MongoDB and more, with stars, licence, last update and install command side by side.
Best MCP Servers for Browser Automation: Playwright, Chrome DevTools (2026)
Compare MCP servers that let AI agents drive or inspect a browser: Playwright MCP, Chrome DevTools MCP, Browserbase and more, with licence, stars and install commands.
