apache/burr

What it solves

Apache Burr makes it easier to develop stateful applications that require complex decision-making, such as AI agents, chatbots, and simulations. It provides a structured way to manage application state and track logic flows without forcing a specific LLM or data management strategy on the developer.

How it works

Developers express their application as a state machine (a graph or flowchart) using simple Python functions called "actions". These actions read from and write to a shared state. The framework provides an ApplicationBuilder to define the transitions between these actions and the initial state. It also includes a telemetry UI for real-time monitoring, tracing, and debugging of the execution flow.

Who it’s for

It is designed for Python developers building AI-driven applications (like RAG chatbots or interactive assistants) or non-LLM stateful workflows (like time-series forecasting simulations or hyperparameter tuning) who need a robust way to handle state and trace execution.

Highlights

• Framework Agnostic: Works with any LLM or Python library, including integrations with Apache Hamilton.
• State Management: Built-in support for saving and loading application state via pluggable persisters.
• Observability: Includes a dedicated UI for viewing execution telemetry and debugging in real time.
• Low Abstraction: Uses a dependency-free core library that relies on standard Python functions.