PyRUA-Lean
Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success but 65% Fewer Tokens
- computer-use-agent
- gpt-6-astra
- post-training
- robot-use-agent
- robotics
- rsi
- vla
- recursive-self-improvement
- self-evolving
- self-evolving-agent
- robodojo
- vision-language-action
- vision-language-model
- token-efficiency
- Stars
- 43
- Forks
- 1
- + today
- +1
- Created
- 21d
Ranking data as of October 16, 2026 (UTC).
Star History
Today, hour by hour
01
Overview
Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success but 65% Fewer Tokens It ranks #1632 on GitTiger, gaining +1 star on October 16, 2026 (UTC).
The project is written in Python and has 1 fork. It was created 21d ago.
Installation
git clone https://github.com/DAGroup-PKU/PyRUA-Lean.git
cd PyRUA-Lean
# see README for setup