Human-Agent-Society/reef

Infrastructure for continually self‑improving agents [](https://github.com/Human-Agent-Society/reef/actions/workflows/ci.yml) [](https://pypi.org/project/reef-infra/) [](pyproject.toml) [](LICENSE) English | 中文 Reef is the first open-source infrastructure for continual self-improving agents. It connects agent inference, feedback, learning, and versioned delivery. Use it to train model weights with Slime and SGLang, or improve an agent's harness, including its prompts, rules, and skills. 🚀 Get started | 🗺️ Roadmap | 🗓️ Office Hours | 📣 Launch post | 💬 Join Discord | 📱 Join WeChat Group Use Reef when you want your agent to keep improving simply by learning from how you interact with your agent. Reef processes each learning cycle in four steps. The table also shows which modules implement each step. We recommend uv for managing packages, and the commands below use it. Use the source checkout for development and for the training examples below. Reef supports two learning surfaces: model weights and agent harnesses. The deployment's recipe determines…