#120120th of 153 in Agent frameworks and SDKs
burr
Python state-machine library for stateful agents and chatbots, with a tracing UI
- Stars
- 2.6k
- License
- Apache-2.0
- Last commit
- Nov 2026
- Last release
- Aug 2026
- Language
- Python
1,968 on 25 Apr 20262,604 on 14 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Apache Burr (incubating) lets you write LLM apps, agents and simulations as state machines built from plain Python functions with declared reads and writes. It ships a dependency-free core library, a local telemetry UI for tracing and debugging runs, and pluggable persisters for saving and loading application state. It does not prescribe how you call models or manage data.
Who it is for: Python developers building stateful LLM agents who want tracing and persistence
Strengths
- Core library has no dependencies; actions are plain Python functions with declared reads/writes
- Bundled UI traces and monitors execution in real time; started with the `burr` command
- Pluggable persisters save and load state, e.g. for agent memory
- Not tied to LLMs; examples include simulations and hyperparameter tuning
Weaknesses
- No asynchronous event-based orchestration, per its own comparison table
- Retries and exception management are listed as planned, not built in
- Hosted deployment and FastAPI integration are roadmap items; Burr Cloud is waitlist only
- Python only; requires Python 3.10+
What it needs
- no GPU
- Needs OpenAI API key (optional, for the demo chatbot)
- Models: Any LLM via user code, OpenAI (demo chatbot)
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Agent frameworks and SDKs
See all 153| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 96 out of 100 |
| 2 | copilotkitReact and Angular SDK for adding agent chat and generative UI to apps | 92 out of 100 |
| 3 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 92 out of 100 |
| #4 | mastraTypeScript framework for building AI agents, workflows and MCP servers | 92 out of 100 |
| #5 | browser-usePython library that lets an LLM agent control a web browser | 90 out of 100 |