yjyddq/RiOSWorld
Benchmark for risks of computer-use agents
View on index · View in 3D Map
Related repos
- Benchmark for agentic LLM and VLM reasoning on games
- Orchestrates agents and skills for Claude Code
- benchmarking agents on real cybersecurity CTF tasks
- Orchestrates agents from 90,000 skills
- AI agents for internet research and task execution
- Security testing framework for autonomous agents
- Automates security operations with AI agents
- Virtual environment for evaluating scientific discovery agents
- curated papers on building the agentic web with AI agents
- Benchmark for cross-platform embodied agents
