GitHub repo leaderboard by stars, growth rate and activity.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
The batteries-included agent harness.
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
Harness engineering beginner tutorial, from 0 to 1
A local multi-agent harness that works with your existing Claude Code, Codex subscriptions, allows you to run an office of agents
Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes.
The open-source agent harness - the runtime layer that turns an LLM into a working agent.
Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs | Go | 90,410 | last pushed 24 hours ago | |
| 2 | Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities. | Python | 34,723 | last pushed 23 hours ago | |
| 3 | The batteries-included agent harness. | Python | 29,245 | last pushed 23 hours ago | |
| 4 | How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end. | Python | 19,838 | last pushed Yesterday | |
| 5 | Harness engineering beginner tutorial, from 0 to 1 | TypeScript | 15,023 | last pushed 2 weeks ago | |
| 6 | Multi-Agent Harness for Production AI | Python | 11,029 | last pushed 5 days ago | |
| 7 | A local multi-agent harness that works with your existing Claude Code, Codex subscriptions, allows you to run an office of agents | TypeScript | 6,743 | last pushed 2 days ago | |
| 8 | Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes. | Python | 5,859 | last pushed 23 hours ago | |
| 9 | The open-source agent harness - the runtime layer that turns an LLM into a working agent. | TypeScript | 5,356 | last pushed Yesterday | |
| 10 | Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration. | Python | 4,092 | last pushed 2 days ago |
All · 11,474