Meirtz/Shinken
Train computer-use agents end-to-end on real desktops, at scale: a high-performance runtime where 8K+ live environments on one laptop thread.
GitHub repository with 14 stars and 0 forks.
Language: Python
Topics: agent-infrastructure, ai-agents, computer-use, criu, desktop-automation, docker, gym, llm-agents, reinforcement-learning, rl-environment