CAMEL (Communicative Agents for Mind Exploration of Large Language Model Society) is an open-source framework and research community focused on multi-agent systems and scaling laws of agents. It provides infrastructure for building agent systems with roles, hierarchies, memory, and tool use, integrating with 40+ LLMs and multiple vector databases. Notable projects include OASIS (simulations with 1 million agents), OWL (workforce learning), and CRAB (computer operations). It is primarily a research and developer framework rather than a commercial product. Key features: - Role-playing multi-agent conversations and task automation - Integration with 40+ LLM providers and multiple vector stores - OASIS: social simulation framework supporting 1 million agents - OWL: optimized workforce learning for real-world task automation - Workforce modeling with roles, hierarchies, and statefulness - Tools for code execution, web browsing, and data analysis
Free and open source (pip install camel-ai). No commercial tiers listed.