Raven: Open-Source Multi-Agent Ecosystem That Auto-Builds and Evolves Harnesses of Harnesses
EverMindAI · hf · 2026-09-30
Raven, an open-source multi-agent ecosystem from EverMindAI, treats each executable model–harness pair as a composable unit of intelligence. A Host Agent decomposes goals, matches subtasks to specialized agents, and coordinates execution; a host archive and EverOS preserve experience across tasks while Skill Forge turns it into reusable procedures. The paper establishes sufficient conditions for such composition to expand reliable task coverage, and Raven significantly outperforms state-of-the-art agent systems on complex long-horizon tasks.
Related event: Open-Source Raven Turns Recursive Self-Improvement into Working Engineering(3 posts)→
More from coding & agent
- A new auto-research loop that bootstraps the shape of the best possible result — burny_tech · 2026-09-30
- Stack Overflow joins OpenAI DevDay to share how Codex sped up its new architecture — pchandrasekar · 2026-09-30
- Models improving doesn't obsolete your agentic coding scaffolding, argues pushback on viral take — max_paperclips · 2026-09-30
- Building a Code Review Agent That Learns From Feedback With Groq and Hindsight — pasulabhavya · 2026-09-30
- Open-Dots, an open-source clone of OpenAI's Dots, hits 4,500 GitHub stars in 24 hours — matchaman11 · 2026-09-30
- Graphsub pitches in-memory graph DB for agent data: don't trust one AI corp with it all — arthurcolle · 2026-09-30