repowiserepowise

Command-line tool

apache / burr

Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.

★ 2,600stars on GitHubPythonApache-2.0

This connects Repowise to apache/burr's code. It does not install burr.

Repowise maps public repos from their source. Not affiliated with apache. What is Repowise?

github.com/apache/burrIndexed at d887c2f

What is burr?

burr is a Python library for building applications that make decisions, such as chatbots, agents and simulations. It lets you express an application as a state machine made of simple Python functions, so each step and transition is explicit. The core is written in Python and the project also ships a UI for tracing and monitoring execution. To install it, run git clone https://github.com/apache/burr && cd burr/examples/hello-world-counter and follow the steps below. Its code health is 7.7 out of 10 (Good), ranked #85 of 4,000+ indexed repos. The last commit to burr was on Jul 21, 2026, and 56 people have contributed.

As of commit d887c2f, indexed Jul 22, 2026. What it is comes from a model reading the README; the rest is measured from the source and git history, not from the maintainer.

For agentsburr.md

Repo facts: type, license, health, rank, contributors
burr facts
TypeCommand-line tool
LicenseApache-2.0
Code health7.7 / 10 (Good)
Health rank#85 of 4,000+ indexed repos
Last commitJul 21, 2026
Contributors56
Bus factor2
Size513 files, 61,991 lines

Install burr

Commands copied from the README

  1. 1Clone the repository and go to the hello-world-counter example.
    git clone https://github.com/apache/burr && cd burr/examples/hello-world-counter
  2. 2Run the counter example from its directory and watch its trace appear in the UI.
    python application.py

Releases on GitHub (latest v0.43.0-incubating, Aug 29, 2026)

Full install notes on GitHub

Explore burr

Ask about this code in your agent

This connects Repowise to burr's code. It does not install burr. To install burr, use the install steps.

Useful if you want to change or fork burr: your agent can ask how it is put together and get answers that cite its files.

Ask about burr

Answers come from burr's README and source, with the files they cite. Two free answers a day without an account.

Want this for your own codebase? Map your repo free

About this page

Get a page like this for your own codebase

Repowise built this map of apache/burr from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Free for 2 public repos, with a page like this one. No card. See how Repowise works

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed. Star Repowise on GitHub

apache/burr FAQ

What is burr?

burr is a Python library for building applications that make decisions, such as chatbots, agents and simulations. It lets you model an application as a state machine built from simple Python functions and includes a UI for tracing execution.

How does burr work?

burr expresses an application as a state machine, which is a graph or flowchart of steps. You can add pluggable persisters to save and load application state, and the UI shows execution telemetry in real time.

How do I install burr?

burr installs from PyPI with pip install "apache-burr[start]". After installing, running the burr command starts the telemetry UI server. See the install steps

What language is burr written in?

burr is written in Python, which is its primary language. TypeScript files also appear in the repository alongside the Python code.

How is the burr code organized?

The main package is the burr directory, with the state machine core in burr/core and the command line entry point in burr/cli. Runnable examples live in the examples directory and tests in the tests directory.

Who is burr for?

burr is for developers building applications that make decisions, including LLM-based chatbots and agents. It also supports non-LLM uses such as time-series forecasting simulations and hyperparameter tuning.

What license does burr use?

burr is licensed under Apache-2.0.

Code health

7.7out of 10Good

Hotspots average 2.9, the place fixes pay off most.

On the leaderboards:#2 of 5 Agent frameworks#20 of 71 Python repos

Key features of burr

  • Builds applications that make decisions from simple Python building blocks.
  • Includes a UI that tracks, monitors and traces a running system in real time.
  • Provides pluggable persisters to save and load application state, such as memory.
  • Lets you express an application as a state machine, a graph or flowchart of steps.
  • Supports hooks and integrations with observability and storage vendors, and custom actions that call libraries such as Apache Hamilton.

How apache/burr works

Your application is written as a state machine, with the core logic in the burr package, and burr/core/action.py defines the actions that the state machine runs. Running the burr command starts the server defined in burr/cli/__main__.py, which opens the telemetry UI. burr/tracking/server/run.py is an entry point for the tracking server. The telemetry directory contains the UI code, and the tests directory holds the test suite. Runnable examples such as examples/hello-world-counter show how the pieces fit together.

The codebase has 513 files and 3,485 symbols in 8 modules, led by Python, TypeScript and Terraform. Code health is 7.7 out of 10, rated good.