Lists (4)
Stars
RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents
ParaGUIBench: Benchmarking Parallel Execution and Coordination for GUI Agents
Xmart青年论坛仓库，存放历史学生论坛和前沿讲座的视频回放和讲义，获取最新Xmart预告欢迎关注公众号【XLANCE Lab】
[NeurIPS'26] "Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents"
CUA-Gym-Hub: mock web apps as reproducible RL training environments for computer-use agents
Scalable pipeline for synthesizing verifiable RLVR training data for computer-use agents
Standalone guest-side server for OSWorld desktop environments
👾 Open Computer Use – Open-Source Alternative to Codex Computer Use
Gym-Anything: Turn any Software into an Agent Environment
你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.
"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
"ClawWork: OpenClaw as Your AI Coworker - 💰 $15K earned in 11 Hours"
A benchmark environment for fully cooperative human-AI performance.
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
Autonomous AI development loop for Claude Code with intelligent exit detection
Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.
"AI-Trader: 100% Fully-Automated Agent-Native Trading"
Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours
A Reproduction of GDM's Nested Learning Paper
Benchmark for Agentic Powerpoint Editing Tasks
Add virtual monitors to your windows 10/11 device! Works with VR, OBS, Sunshine, and/or any desktop sharing software.
[COLM 2025] EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees