OpenRSI agents land 3 optimizations merged upstream into SGLang-Omni
yuz9yuz · x · 2026-10-08
OpenRSI announced a milestone: three agent-generated optimizations passed maintainer code review and were merged upstream into SGLang-Omni. The companion open-source RSI Harness runs ultra-long-horizon RSI tasks in Harbor format on local Docker (no GPU needed) or multi-node GPU clusters — agents like Claude Code or Codex iterate inside a persistent Work container while submissions are scored in a fresh Judge container, with the best-scoring result kept. The outer loop is the Harness; the inner agent is swappable.
Related event: AI Agent Optimizations from OpenRSI Merged into SGLang-Omni Upstream(2 posts)→
More from coding & agent
- Ramp's hidden markdown-file offer read only by AI actually worked, customers claimed it — gaganghotra_ · 2026-10-08
- Creator revives a dead Notion course by feeding it to Codex as an interactive app — RichardsonDx · 2026-10-08
- Gary Bernhardt: AI 'factories' repeat the microservices over-engineering mistake — sergeykarayev · 2026-10-08
- Hierarchical RL with mixed discount rates may unlock long-horizon agent tasks — jessi_cata · 2026-10-08
- Graph-MIND: local MCP memory server hits 88.8% LongMemEval with zero LLM calls at write time — BrilliantGrocery8233 · 2026-10-08
- dotey's Claude Code workflow: Fable as Tech Lead delegating and reviewing for Opus — dotey · 2026-10-08