đ« CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
Python agentai-societiesartificial-intelligencecommunicative-aicooperative-aideep-learninglarge-language-modelsmulti-agent-systemsnatural-language-processing
title: "Introduction" icon: rocket description: | CAMEL-AI is an open-source community for finding the scaling laws of agents for data generation, world simulation, and task automation.
What is CAMEL-AI?
CAMELâAI is an openâsource, modular framework for building intelligent multiâagent systems. It provides the primitives to:
- Create Agents that reason, plan, and act
- Compose Societies of agents with defined roles
- Integrate Interpreters for code execution and analysis
- Manage Memory for longâhorizon context and learning
- Orchestrate RetrievalâAugmented Generation (RAG) pipelines
- Generate Synthetic Data at scale with selfâinstruct and verifier loops
- Simulate Worlds and agent interactions in environments like social networks
Core Components
- Agents: Atomic reasoning units driven by LLMs, capable of tool calls and decisionâmaking
- Societies: Coordinator layers that assign roles, delegate tasks, and manage collaboration
- Interpreters: Execution backends (Python, shell, browsers) for live code evaluation and automation
- Memory & Storage: Persistent context layers for chat history, tool outputs, and learned knowledge
- RAG Pipelines: Combine chunking, retrieval, and generation for grounded, accurate responses
- Synthetic Data Engines: Selfâinstruct, ChainâofâThought, and Source2Synth pipelines with verifiers
- World Simulation: Platforms like Oasis for largeâscale multiâagent social simulations
- Task Automation: Benchmarks like CRAB for realâworld multiâstep software workflows