Reef, open-source infra for continually self-improving agents, hits 5K GitHub stars in a week
pliang279 · x · 2026-09-26
- Reef, an open-source infrastructure for continually self-improving agents, released v0.1.1 after crossing 5K GitHub stars in a week (1.6K added), with 35 contributors so far (now 5.7K stars).
- Reef connects agent inference, feedback, learning, and versioned delivery: it supports training model weights with Slime and SGLang, or improving the agent harness itself — prompts, rules, and skills — so agents keep learning from user interactions.
- Maintained by the Human-Agent-Society org, with a roadmap, Discord, and launch post.
More from coding & agent
- Harness engineering: the key discipline for building reliable AI agents — techNmak · 2026-09-26
- Feeding PTX ISA to LLMs: Converting Figures to ASCII Art with Gemini — bingxu_ · 2026-09-26
- Merge Claims Its MCP Connectors Match or Beat Public MCPs, Cut Tokens 24% — shensi · 2026-09-26
- Define Dimensions First: Hamel Husain's Method for Synthetic Eval Data — HamelHusain · 2026-09-26
- starrocks-mcp: read-only MCP server to query StarRocks databases via Claude — modelcontextprotocol · 2026-09-26
- AI Trips plans travel collaboratively with AI via MCP tools — modelcontextprotocol · 2026-09-26