CrewAI is a leading open-source framework for orchestrating role-playing autonomous AI agents. With over 47,000 GitHub stars and 100,000+ certified developers, CrewAI enables developers to build multi-agent systems where agents assume specific roles, collaborate, and execute complex tasks autonomously.
License: MIT
GitHub: joaomdmoura/crewAI
- 🎭 Role-Playing Agents - Define agents with specific roles, goals, and backstories
- 🤝 Multi-Agent Collaboration - Agents work together to complete tasks
- 📋 Task Management - Break down complex tasks with expected outputs
- 🔧 Tool Integration - Connect agents to external tools and APIs
- 🧠 Process Control - Sequential, hierarchical, and custom workflows
- 📊 Memory & Context - Share context and memory between agents
- 🔌 Extensible - Custom tools, providers, and integrations
- 🚀 Standalone & Lean - Built from scratch, no LangChain dependencies
- ⚡ High Performance - Optimized for speed and minimal resource usage
- Research Teams - Multiple agents for literature review and analysis
- Content Creation - Collaborative writing and editing workflows
- Data Analysis - Multi-agent data processing and insights
- Customer Support - Tiered support agent hierarchies
- Software Development - Code review, testing, and documentation teams
| Component |
Technology |
| Language |
Python (98.4%), JavaScript (1.2%) |
| Package Manager |
pip, uv (recommended) |
| Deployment |
Python application (no official Docker image) |
| LLM Providers |
OpenAI, Anthropic, Google, Azure, Ollama, 20+ more |
| Integrations |
LangChain, LlamaIndex, 50+ tools |
| Component |
Minimum |
Recommended |
| OS |
Linux, macOS, Windows |
Linux (Ubuntu 20.04+) |
| Python |
3.10+ |
3.11+ |
| CPU |
1 core |
2+ cores |
| RAM |
1 GB |
4+ GB |
| Disk |
500 MB |
2+ GB |
- ✅ Open-source (MIT License)
- ✅ Active development (v1.10.1 - March 4, 2026)
- ✅ 47k+ GitHub stars, 6.1k forks
- ✅ 141+ releases, 2,037+ commits
- ✅ PyPI package:
crewai
- ✅ 297+ contributors
- ✅ 100,000+ certified developers
- ✅ CrewAI AMP Suite available for enterprise (cloud/on-premise)
- ℹ️ No official Docker image - deploy as Python application
¶ History and References
Any questions?
Feel free to contact us. Find all contact information on our contact page.