Physical AI runtime for embodied agents — governed action, verified experience, physical memory, and skill evolution.
Latest release v1.3.0 — ROSClaw v1.3.0 — Internal Alpha · 17 Sept 2026
4 files for Codex, Claude Code and OpenCode: rosclaw-simforge, rosclaw, rosclaw AGENTS.md, rosclaw CLAUDE.md — 3,659 tokens loaded in every session.
AGENTS.md A 1,903 tok CLAUDE.md A 1,756 tok .agents/skills/rosclaw-simforge/SKILL.md A 97 tok .agents/skills/rosclaw/SKILL.md D 50 tok These files are ros-claw/rosclaw's own configuration — they tell Codex, Claude Code and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.