camel-ai/crab
Benchmark for cross-platform embodied agents
View on index · View in 3D Map
Related repos
- Multi-agent framework for building and running AI agents and agent societies
- simulate a million bots in social networks
- multi-agent framework for automating tasks with AI agents
- Self-hosted sandboxing for AI agent code execution
- Benchmark evaluates LLMs as agents
- locally running AI agent framework with code sandbox, research, coding, and data analysis
- Framework for reproducible benchmarking of web agents
- Reinforcement fine-tuning for UI agents
- Multi-agent runtime for orchestrating AI agents
- List of open-source tools to build AI agents
