# Camel AI — Multi-Agent Role-Playing Framework

> Build multi-agent systems where AI agents collaborate through role-playing. CAMEL enables autonomous cooperation between agents with structured communication protocols.

## Install

Save the content below to `.claude/skills/` or append to your `CLAUDE.md`:

## Quick Use

```bash
pip install camel-ai
```

```python
from camel.societies import RolePlaying

session = RolePlaying(
    assistant_role_name="Python Programmer",
    user_role_name="Stock Trader",
    task_prompt="Develop a stock trading bot that uses moving averages.",
)

# Agents collaborate autonomously
chat_history = []
input_msg = session.init_chat()
while True:
    assistant_response, user_response = session.step(input_msg)
    chat_history.append(assistant_response.msg)
    if assistant_response.terminated or user_response.terminated:
        break
    input_msg = user_response.msg
```

## What is CAMEL?

CAMEL (Communicative Agents for "Mind" Exploration of Large Language Model Society) is a multi-agent framework where AI agents collaborate through role-playing. Each agent assumes a specific role and they communicate through structured protocols to solve complex tasks autonomously. Unlike single-agent systems, CAMEL enables emergent problem-solving through agent interaction.

**Answer-Ready**: CAMEL is a multi-agent role-playing framework for LLMs. Agents assume roles (programmer, researcher, designer) and collaborate autonomously through structured communication. Supports tool use, RAG, and multiple LLM backends. Research-backed by KAUST. 7k+ GitHub stars.

**Best for**: Researchers and developers building collaborative AI agent systems. **Works with**: OpenAI, Anthropic Claude, open-source models. **Setup time**: Under 3 minutes.

## Core Features

### 1. Role-Playing Sessions

```python
from camel.societies import RolePlaying

# Define roles and task
session = RolePlaying(
    assistant_role_name="Data Scientist",
    user_role_name="Business Analyst",
    task_prompt="Analyze customer churn and build a prediction model.",
)
```

### 2. Agent Toolkits

```python
from camel.toolkits import SearchToolkit, CodeExecutionToolkit

# Equip agents with tools
agent = ChatAgent(
    system_message="You are a research assistant.",
    tools=[SearchToolkit().get_tools(), CodeExecutionToolkit().get_tools()],
)
```

### 3. Workforce (Multi-Agent Teams)

```python
from camel.workforce import Workforce

workforce = Workforce("Development Team")
workforce.add_role("architect", "Design system architecture")
workforce.add_role("developer", "Implement features")
workforce.add_role("tester", "Write and run tests")
result = workforce.process("Build a REST API for user management")
```

### 4. RAG Integration

```python
from camel.retrievers import AutoRetriever

retriever = AutoRetriever(vector_storage_local_path="./knowledge")
retriever.ingest("docs/")
# Agents can now query the knowledge base during collaboration
```

## Use Cases

| Use Case | Roles |
|----------|-------|
| Software Development | Architect + Developer + Tester |
| Research | Researcher + Critic + Writer |
| Data Analysis | Analyst + Domain Expert |
| Content Creation | Writer + Editor + Fact-Checker |

## FAQ

**Q: How does it differ from CrewAI?**
A: CAMEL focuses on role-playing communication protocols with research backing. CrewAI is more production-oriented with sequential/parallel task execution.

**Q: Does it support Claude?**
A: Yes, configure Anthropic as the model backend.

**Q: Is it production-ready?**
A: CAMEL is research-first but increasingly used in production. The Workforce API is designed for production use cases.

## Source & Thanks

> Created by [CAMEL-AI](https://github.com/camel-ai). Licensed under Apache 2.0.
>
> [camel-ai/camel](https://github.com/camel-ai/camel) — 7k+ stars

<!-- ZH -->

## Quick Use

```bash
pip install camel-ai
```

Let multiple AI agents collaborate autonomously through role-playing to solve tasks.

## What is CAMEL?

CAMEL is a multi-agent role-playing framework. Agents each take on a role (programmer, researcher, designer) and collaborate autonomously through structured communication.

**TL;DR**: Multi-agent role-playing framework. Agents take on different roles and collaborate autonomously. Supports tool calls and RAG. Research-backed by KAUST. 7k+ stars.

**Best for**: Researchers and developers building collaborative AI agent systems.

## Core Features

### 1. Role-Playing Sessions
Define roles and tasks; agents interact autonomously.

### 2. Tool Equipping
Equip agents with tools like search and code execution.

### 3. Workforce Teams
Multi-role teams handle complex tasks.

## FAQ

**Q: How does it differ from CrewAI?**
A: CAMEL leans toward research and role-based communication protocols; CrewAI leans toward production task execution.

## Source & Thanks

> [camel-ai/camel](https://github.com/camel-ai/camel) — 7k+ stars, Apache 2.0

---
Source: https://tokrepo.com/en/workflows/camel-ai-multi-agent-role-playing-framework-b532d25b
Author: Agent Toolkit