Burr Framework用于构建有状态、决策式应用（如代理和聊天机器人）的开源Python框架

4.3 (4)

审阅者 Daniel Nikulshyn·更新 2026年7月

Open Source Python AI Agents Framework Observability Developer Tools State Management LLM

概览

Burr Framework 是一个 Python 库，适用于需要随时间做出决策的应用程序，例如聊天机器人、AI 代理、仿真和工作流引擎。它将程序建模为状态机，允许开发者定义作用于共享状态对象的动作和转换，从而更易于理解复杂的控制流。该框架内置了可观测性工具、用于查看运行的本地 UI，并支持持久化，以便应用可以暂停、恢复并逐步调试。由于 Burr 对所使用的 LLM 或库不做任何强制限制，因而可与大多数流行的 Python AI 生态集成。它非常适合想要对代理逻辑进行显式控制，而非依赖黑盒编排的团队；同时也适用于重视可追溯性和可测试性的生产系统。

主要功能

具有操作和转换的状态机抽象
用于检查执行的本地遥测UI
状态持久性和可恢复性
流式和异步操作支持
与常见的LLM和ML工具集成
用于日志记录、监控和测试的钩子

价格

模型: Free
分类: 本当常用服务的形嵻箥别
评分: 4.3 / 5 (4)

使用场景

构建具有可追溯逻辑的有状态聊天机器人

将对话流程建模为明确的状态机，带有操作和转换，使其更容易推理聊天机器人行为，并通过本地遥测UI调试运行。

开发决策式AI代理

创建在步骤中管理共享状态的AI代理，支持流式、异步操作以及与Python生态系统中的任何LLM库集成。

运行可恢复的工作流引擎

使用状态持久性暂停、恢复和逐步调试长期运行的工作流或仿真，实现复杂控制流的可靠恢复和检查。

为AI应用程序提供监测和测试

利用内置的日志记录、监测和跟踪钩子观察生产AI应用程序，并通过可复制、可检查的运行验证行为。

优点 & 缺点

优点

明确的状态机模型使逻辑易于理解
内置的跟踪UI用于调试运行
框架无关 - 可与任何LLM或库一起使用
支持持久性、流式处理和异步操作
开源且轻量级

缺点

需要Python及其抽象的学习
比更高级别的代理框架 less即插即用
比大竞争对手更小的社区

评测

4.3

4 个评分的平均值。

登录以留下评测。

Priya Nair

May 2, 2026

Does the job

Pretty happy overall. Local telemetry UI for inspecting executions just works and built-in tracing UI for debugging runs. Less plug-and-play than higher-level agent frameworks can be annoying, but no dealbreakers — I'd recommend it to a friend without hesitating.

Ethan Brooks

Mar 21, 2026

Compared a few options

Evaluated this against two competitors. Where it wins: local telemetry UI for inspecting executions and explicit state-machine model makes logic easy to follow. Where it lags: requires Python and some learning of its abstractions. On balance the feature set — especially local telemetry UI for inspecting executions — justifies the 5 stars for our use case.

Tariq Aziz

Jan 27, 2026

Use it every day

Honestly didn't expect to like it this much. State persistence and resumability is exactly what I needed, and open source and lightweight. I do wish smaller community than larger competitors, but I reach for it almost every day now and it just clicks.

Diego Fernández

Oct 16, 2025

Solid for our team

We rolled this out across the team last quarter and built-in tracing UI for debugging runs. State persistence and resumability fits neatly into how we already work, and integrations with common LLM and ML tools removed a step we used to do by hand. Smaller community than larger competitors, which is the main caveat, but it has held up under daily use.

问答

Why the name Burr?

Apache Burr is named after Aaron Burr, founding father, third Vice President of the United States, and historical opponent of Alexander Hamilton. The name reflects the project's origins as a harness to handle state between executions of Apache Hamilton DAGs (because DAGs don’t have cycles). Over time, Burr proved useful for a wide array of applications, leading to its broader release.

Asked by Naomi Suzuki · Nov 13, 2025

What can you do with Apache Burr?

Apache Burr can be used to power a variety of applications, including: 1. A simple GPT‑like chatbot. 2. A stateful RAG‑based chatbot. 3. An LLM‑based adventure game. 4. An interactive assistant for writing emails. It also supports non‑LLM use‑cases such as time‑series forecasting simulations and hyperparameter tuning. Using hooks and integrations you can integrate with any of your favorite vendors (LLM observability, storage, etc.) and build custom actions that delegate to your favorite libraries (like Apache Hamilton). Burr does not build models, query APIs, or manage data for you; it helps you tie these components together in a scalable, logical way. It includes out‑of‑the‑box integrations and tooling to build a UI in Streamlit and watch your state machine execute.

Asked by Valentina Marino · Nov 1, 2025

How does Apache Burr work?

With Apache Burr you express your application as a state machine (i.e. a graph/flowchart). You can (and should!) use it for anything in which you have to manage state, track complex decisions, add human feedback, or dictate an idempotent, self-persisting workflow. The core API is simple – the Burr hello-world looks like this (plug in your own LLM, or copy from the docs for gpt‑X). Apache Burr includes: 1. A dependency‑free low‑abstraction Python library that enables you to build and manage state machines with simple Python functions. 2. A UI you can use to view execution telemetry for introspection and debugging. 3. A set of integrations to make it easier to persist state, connect to telemetry, and integrate with other systems.

Asked by Carlos Mendoza · Oct 27, 2025