Build reliable, intelligent agents with our lightweight framework that goes beyond prompting and enforces rules.
- 🔀 Dynamic workflows - Use simple decorators to design multi-agent systems with advanced patterns like parallelism, retries, and replanning
- ⚖️ Agents with constraints - Preserve your agent's reasoning abilities while enforcing deterministic rules instead of suggesting behavior
- 📋 Declarative orchestration - Define complex agent systems in YAML for more predictable and maintainable orchestration
- 📊 Pluggable observability - Integrate with your existing stack in minutes with native OpenTelemetry support for auditing and monitoring
- 💻 Python and TypeScript support - Feature parity between languages lets teams build with the tools they already know and love
- 🔌 MCP and A2A native - Build MCP-compatible components, equip agents with MCP tools, and interoperate with any MCP or A2A agent
Deploy and share agents with open infrastructure, free from framework or vendor lock-in.
- ⚡ Instant agent UI - Generate a shareable front-end from your code in minutes. Focus on your agent's logic, not UI frameworks
- ☁️ Effortless deployment - Go from container to production-ready. We handle database, storage, scaling, and RAG so you can focus on your agent
- 🎮 Multi-provider playground - Test across OpenAI, Anthropic, Gemini, IBM watsonx, Ollama and more. Instantly compare performance and cost to find the optimal model
- 🌐 Framework-agnostic - Run agents from LangChain, CrewAI, and more on a single platform. Enable cross-framework collaboration without rewriting your code
Want to create your own AI agents? Start with the framework.
What to deploy and share your AI agents with others? Check out Agent Stack.
Developed by contributors to the BeeAI project, this initiative is part of the Linux Foundation AI & Data program. Its development follows open, collaborative, and community-driven practices.
