Burr
Build stateful AI agents and applications as state machines, with a built-in tracing UI
Burr is a Python framework for building stateful AI applications and agents, modeling them as state machines of actions and transitions defined with plain functions and decorators. It covers chatbots, agents, and simulations without a domain-specific language.
It persists state to disk, databases, or custom backends, supports checkpoints, human-in-the-loop, parallel execution, and branching, and ships a built-in UI for real-time monitoring, tracing, and replay. It integrates with OpenAI, Anthropic, LangChain, FastAPI, and Pydantic. Apache 2.0 (incubating), originally built by DAGWorks.
Pricing: Free
Burr Alternatives
Explore 31 products in the Frameworks & Stacks category. View all Burr alternatives.
Mastra
TypeScript-first AI framework for building agents, RAG pipelines, and workflows
vLLM
High-throughput LLM inference engine with PagedAttention for efficient GPU memory usage
Ollama
Run large language models locally with a single command
Dify
Easily build and operate generative AI applications. Create Assistants API and GPTs based on any LLMs.
Also listed in
Work on Burr? Feature it at the top of Frameworks & Stacks.
Is your product missing?