LMMs Lab open-sources The Harness: one unified framework for computer, robot, and game agents
liuziwei7 · x · 2026-11-15
LMMs Lab (Fei-Fei Li-affiliated group led by Hao Li / Zhenqiang "Kepler" — actually from Liu Ziwei's lab) open-sourced "The Harness," a unified framework for building, testing, and advancing general-purpose agents across diverse environments, covering computer-use, robot-use, and game-play agents. More designs, results, and demos will be opened to the community over time.
More from coding & agent
- shadcn authors designed UI libraries by inspecting model weights, making agents better — cramforce · 2026-11-15
- Google launches Gemini Decisions API with Gemini Decision 1, zero output-token billing — sebkrier · 2026-11-15
- Claude Code advisor: Fable 5.2 adds 1.7 points for Opus 5.5 at 2.1x cost — and can hurt — socialwithaayan · 2026-11-15
- Lessons from building 5 deterministic MCP servers for finance/data tasks — Ltx_23 · 2026-11-15
- Connecting Claude to Google Search Console: a weekly automated SEO-fix loop — martyamark · 2026-11-15
- The T.R.U.S.T. check: deciding which jobs you can safely hand to your AI bots — bfrench · 2026-11-15