RA

robot-agent-exploration/skills-lib

Developer tools

このページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。 原文を見る

14 stars 品質 51 トレンド 34

Task skills robot agents learned on real robots, one library per embodiment

概要

RAX is the general harness: a coding agent (Claude Code or Codex CLI) drives a robot through perception and control tools, with no demonstrations, and compiles what worked into code. Each skill is an executable procedure the agent wrote while it explored a task, stored with its preconditions, checks, failure modes and the evidence of its runs (run records and camera frames). A later session, on a new task or in a new scene, reads the library, runs or composes the skills that match, and merges back what it improves. main holds the protocol. , with one folder per skill. Each library's harness lives in the RAX repository, which also documents the robot's tools: real/rainbow and real/franka. 1. Read INDEX.md and open only the skills that match your task. 2. Check each skill's preconditions against your scene. 3. Run its entry through the robot's harness context (ctx).

README

以下は原文 README の抜粋です。原文を見る。


RAX is the general harness: a coding agent (Claude Code or Codex CLI) drives a robot through perception and control tools, with no demonstrations, and compiles what worked into code. This repository keeps what those agents learned on real robots.

Each skill is an executable procedure the agent wrote while it explored a task, stored with its preconditions, checks, failure modes and the evidence of its runs (run records and camera frames). A later session, on a new task or in a new scene, reads the library, runs or composes the skills that match, and merges back what it improves.

 explore a task ──► write a skill ──► merge into the library
        ▲                                     │
        └──── next session reads, reuses ◄────┘
              and composes the skills

🌿 Libraries

main holds the protocol. Each robot embodiment has its own branch, with one folder per skill.

Branch Robot Skills Status
rby1 Rainbow RB-Y1: wheeled base, 6-joint torso, two 7-DoF arms, grippers, head ZED 2i bimanual box and bucket pick-and-place, office-chair tuck, cup stacking, whole-body hand reach, and a six-step room tidy that composes them ✅ 6 skills
franka Franka FR3: one 7-DoF arm, Franka Hand, two exterior cameras and a wrist camera find the cube, air fryer, wipe the table, peg-in-hole, Bandu tower ✅ 5 skills

Each library’s harness lives in the RAX repository, which also documents the robot’s tools: real/rainbow and real/franka.

🚀 Using a skill

git clone -b rby1 https://github.com/robot-agent-exploration/skills-lib.git skill-library
  1. Read INDEX.md and open only the skills that match your task.
  2. Check each skill’s preconditions against your scene.
  3. Run its entry through the robot’s harness context (ctx).
GitHub で README 全文を見る

推奨ツール

別のキーワードを試すか、フィルタを外してください。

インストール

npx skillfish add robot-agent-exploration/skills-lib
MCP 初心者?mcpskill.org のガイドから始めましょう →