Welcome to CAMEL’s documentation!

We design practical artificial general intelligence.

CAMEL emerges as the earliest LLM-based multi-agent framework, and is now a generic framework to build and use LLM-based agents for real-world task solving. We believe that studying these agents on a large scale offers valuable insights into their behaviors, capabilities, and potential risks. To facilitate research in this field, we implement and support various types of agents, tasks, prompts, models, and simulated environments.

Main Documentation

Get Started

• Installation and Setup

Agents

• Creating Your First Agent
• Creating Your First Agent Society
• Embodied Agents
• Critic Agents and Tree Search

Key Modules

• Models
• Message
• Memory
• Tools
• Prompt
• Task
• Loaders
• Storages
• Embeddings
• Retrievers
• Workforce

Cookbooks

• 🐫 CAMEL Create Your First Agent
• 🐫 CAMEL Create Your First Agents Society
• 🐫 CAMEL Society Cookbook
• 🐫 CAMEL Message Cookbook
• 🐫 CAMEL Tools Cookbook
• ‍Table of Content:
• Introduction
• Tool Usage of a Single Agent
• AI Society with Tool Usage
• Conclusion
• 🐫 Using Tools from Composio
• 🐫 CAMEL Memory Cookbook
• 🐫 CAMEL RAG Cookbook
• 🐫 CAMEL Prompting Cookbook
• 🐫 CAMEL Task Generation Cookbook
• 🐫 Using CAMEL to Do Graph RAG with Mistral Models
• 🐫 CAMEL Role-Playing Scraper for Report & Knowledge Graph Generation
• 🐫 CAMEL Video Analysis
• 🐫 Using AgentOps to Track CAMEL Agents

API References

• camel

Indices and tables

• Index

• Module Index

• Search Page

Get Involved

We are always happy to work with friends to continuously move forward with our own competitive edges.

For Research Aficionados: New, rigorous and in-depth research takes time and resources. With access to almost unlimited usage of advanced GPU computes and a team of amazing researchers and engineers, we are bold enough to explore the frontier with patience. Whether you would like to join in our on-going project or have new idea to test, feel free to talk to us and see how we may work together.

For Coding Enthusiasts: Whether you want to introduce new features, enhance the infrastructure, improve documentation, asking issues, add more examples, implement state-of-the-art research ideas, or fix bugs, we appreciate each and every commit. Get started by checking out the Contributing Guidelines on GitHub.

For Interested Humans: Connect with us on Slack or Discord.