Repolode
投稿する
RLinf

RLinf/RPent

An open framework for building embodied agents that use LLM planners, VLA manipulation models and memory to run robot tasks in simulators and on real robots.

GitHub で見る公式サイト
スター
1,554
フォーク
136
未解決の Issue
37
最終コミット
3 時間前

これは何？

RPent (Recursive Physical Agent) is an agentic infrastructure for physical robots. Instead of tying the system to one foundation model, it combines perception, reasoning, memory, execution and self-evolution components into a single physical agent, built on service-oriented, standardized and composable design principles.

The framework lets a planner such as Claude Code or Codex decide how to break a task into steps, while VLA models like Pi0.5, RLDX-1 and LingBot-VLA execute the low-level manipulation primitives. It supports LIBERO-PRO, RoboCasa, RoboTwin and RoboDojo simulators, and Franka and dual-Franka real-robot setups are listed as supported, with SO-101 and YAM marked as planned.

RPent ships a CLI for running predefined tasks, an interactive mode for steering the agent from a terminal, and a live dashboard that streams agent reasoning, camera views and the action timeline. Documentation is available in English and Chinese.

主な機能

  • 01Pluggable planners, including Claude Code, Codex and custom planners.
  • 02Supports VLA models such as Pi0.5, RLDX-1 and LingBot-VLA as action primitives.
  • 03Runs on LIBERO-PRO, RoboCasa, RoboTwin and RoboDojo simulators.
  • 04Supports Franka and dual-Franka real-robot setups.
  • 05Interactive CLI mode for steering the agent during a run.
  • 06Live dashboard with agent reasoning, camera views and action timeline.

ユースケース

  • Benchmarking long-horizon manipulation methods on LIBERO-PRO or RoboCasa.
  • Researching self-evolving or memory-guided embodied agents.
  • Prototyping agentic robot control on Franka arms before production deployment.

トピック

#embodied-ai#robotics#agentic-ai#vla#robot-simulation#reinforcement-learning#llm-agents#embodied

よくある質問

RPent とは？
An open framework for building embodied agents that use LLM planners, VLA manipulation models and memory to run robot tasks in simulators and on real robots. RPent (Recursive Physical Agent) is an agentic infrastructure for physical robots. Instead of tying the system to one foundation model, it combines perception, reasoning, memory, execution and self-evolution components into a single physical agent, built on service-oriented, standardized and composable design principles.
RPent は無料で使えますか？ライセンスは？
RPent は Apache-2.0 ライセンスのオープンソースです。商用製品で使う前にライセンス条件を確認してください。
RPent は今もメンテナンスされていますか？
活発にメンテナンス中。RPent の最終コミットは 2026年10月19日 です。
RPent は何に使えますか？
Benchmarking long-horizon manipulation methods on LIBERO-PRO or RoboCasa. Researching self-evolving or memory-guided embodied agents. Prototyping agentic robot control on Franka arms before production deployment.
RPent はどこで入手できますか？
ソースコードとインストール手順は GitHub にあります：https://github.com/RLinf/RPent

概要はプロジェクトの README をもとに AI が生成しています。GitHub の数値は毎日更新されます。

関連プロジェクト