Burr FrameworkOpen-source Python framework za gradnjo aplikacij z notranjim stanjem in odločitvami, kot so agenti in klepetalni roboti.

4.3 (4)

Pregledal Daniel Nikulshyn·Posodobljeno julij 2026

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

Pregled

Burr Framework je Python knjižnica za gradnjo aplikacij, ki morajo sprejemati odločitve skozi čas, kot so klepetalni roboti, AI agenti, simulacije in workflow engines. Modelira programe kot state machines, kar razvijalcem omogoča definiranje dejanj in prehode, ki delujejo na skupnem state object, kar poenostavi razumevanje zapletenega kontrolnega toka. Framework vključuje vgrajena orodja za opazovanje, lokalni UI za pregled zagonov ter podporo za ohranjanje, da lahko aplikacije prekinete, nadaljujete in jih korak za korakom debugate. Ker Burr ni usmerjen glede na to, katere LLM-ji ali knjižnice uporabljate, se integrira z večino priljubljene Python AI stack. Primeren je za ekipe, ki želijo izraden nadzor nad logiko agentov, namesto da bi se zanašale na črno škatlo orchestracije, in za proizvodne sisteme, kjer sta pomembni sledljivost in preizkusljivost.

Ključne funkcije

Abstrakcija stanja z dejanji in prehodi
Lokalni UI telemetrije za pregledovanje izvedb
Vzdrževanje stanja in možnost nadaljevanja
Podpora za pretok in asinhrone akcije
Integracije z običajnimi LLM in ML orodji
Hooki za beleženje, spremljanje in testiranje

Cene

Model: Free
Kategorija: Javni frameworki za učne agente
Ocena: 4.3 / 5 (4)

Primeri uporabe

Izdelaj chatbot z notranjim stanjem in sledljivo logiko

Modeliraj pogovorne tokove kot eksplicitne state machine z dejanji in prehodi, kar olajša razumevanje delovanja chatbota ter razhroščevanje zagnanj prek lokalnega UI telemetrije.

Razvij AI agente z odločitvami

Ustvari AI agente, ki upravljajo skupno stanje med koraki, s podporo za pretok, asinhrone akcije in integracijo z vsako LLM knjižnico v Python ekosistemu.

Izvajaj workflow motorje z možnostjo ponovnega začetka

Uporabi trajnost stanja za prekinitev, ponovno začetek in korak po koraku razhroščevanje dolgotrajnih workflowov ali simulacij, kar omogoča zanesljivo obnovitev in pregledovanje zapletenega kontrolnega toka.

Instrumentiraj AI aplikacije za spremljanje in testiranje

Izkoristi vgrajene hooke za beleženje, spremljanje in sledenje, da opazuješ proizvodne AI aplikacije in potrdiš obnašanje preko ponovljivih, preglednih zagnanj.

Prednosti in slabosti

Prednosti

Jasen model stroja z stanjem olajša sledenje logiki
Vgrajen UI za sledenje za razhroščevanje zagnanj
Neodvisen od frameworka — deluje z vsakim LLM ali knjižnico
Podpira vzdrževanje stanja, pretok in asinhronost
Open-source in lahkotna

Slabosti

Potrebuje Python in nekaj učenja njegovih abstrakcij
Manj plug-and-play kot višji agent frameworki
Manjša skupnost kot večji konkurenti

Ocene

4.3

Povprečje iz 4 ocen.

Prijavi se za oddajo ocene.

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.

Vprašanja

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