ASPIRE is a research framework where coding agents iteratively write and refine sensorimotor skills for robot manipulation tasks in simulation and on real robots.
5400PythonApache-2.0Actualizado hace 3 días
RLinf/RPent
An open framework for building embodied agents that use LLM planners, VLA models and memory to run manipulation tasks in simulators and on real robots.
- Estrellas
- 1,538
- Forks
- 0
- Issues abiertos
- 0
- Último commit
- hace 3 días
Funciones clave
- 01Pluggable planners, including Claude Code, Codex and custom planners.
- 02Supports multiple VLA models such as Pi0.5, RLDX-1 and LingBot-VLA.
- 03Runs tasks in LIBERO-PRO, RoboCasa, RoboTwin and RoboDojo simulators.
- 04Provides Franka and dual-Franka real-robot extensions.
- 05Offers interactive CLI control and a live web dashboard.
Casos de uso
- Researching long-horizon robotic manipulation with LLM-guided agents.
- Prototyping embodied agents before deploying them on Franka robot arms.
- Studying continual or reinforcement learning for self-evolving physical agents.
- Benchmarking VLA models across LIBERO, RoboCasa and RoboTwin tasks.
Temas
Preguntas frecuentes
- ¿Qué es RPent?
- An open framework for building embodied agents that use LLM planners, VLA models and memory to run manipulation tasks in simulators and on real robots.
- ¿RPent es gratuito? ¿Qué licencia tiene?
- RPent es open source bajo la licencia Apache-2.0. Revisa los términos de la licencia antes de usarlo en productos comerciales.
- ¿RPent sigue mantenido?
- Mantenimiento activo. El último commit de RPent fue el 16 oct 2026.
- ¿Para qué puedo usar RPent?
- Researching long-horizon robotic manipulation with LLM-guided agents. Prototyping embodied agents before deploying them on Franka robot arms. Studying continual or reinforcement learning for self-evolving physical agents. Benchmarking VLA models across LIBERO, RoboCasa and RoboTwin tasks.
- ¿Dónde consigo RPent?
- El código fuente y las instrucciones de instalación están en GitHub: https://github.com/RLinf/RPent
Resumen generado por IA a partir del README del proyecto. Las estadísticas de GitHub se actualizan a diario.
Proyectos relacionados
Robotics inference toolkit built on the ApxInf Rust engine, running VLA policies such as PI-0.5 on NVIDIA Jetson and RTX GPUs.
2260PythonApache-2.0Actualizado hace 20 días
AutoGPT is an open-source platform for building, running, and scheduling AI agents that carry out multi-step workflows from plain-English descriptions or a visual builder.
187,7 mil45,9 milPythonOtherActualizado hace 45 minutos
Python framework for building and orchestrating multi-agent systems with sequential, concurrent, graph-based and hierarchical workflows.
7,3 mil1,1 milPythonApache-2.0Actualizado hace 10 horas
A Python library and runnable Jupyter textbook implementing 35 agentic AI architectures, from Reflexion and ReAct to MemGPT and BrowserAgent, on LangGraph.
4,6 mil0Jupyter NotebookMITActualizado hace 4 meses
A curated awesome-list of robotics books, courses, simulators, software libraries, conferences, journals and competitions.
7,2 mil1,1 milOtherActualizado hace 2 años