Catalog Systems Agent frameworks (no first-party memory layer) Burr (DAGWorks)

Burr (DAGWorks)

https://github.com/apache/burr

State-machine framework for agents — state + actions + transitions; lightweight alternative to LangGraph. Created by DAGWorks and donated to the Apache Software Foundation, where it is now Apache Burr (incubating).

Active · Verified 2026-10-29 · fresh as of 2026-10-29 · 35 cited facts, 0 with a third-party source · 3 recorded changes · Suggest a correction

At a glance

Type
State-machine agent framework repo fix
Tier
T3
Section
Agent frameworks (no first-party memory layer)
Created
2024 repo fix
Latest release
v0.43.0 (2026-08-25) — apache-burr registry fix
License
Apache-2.0 registry fix
GitHub
apache/burr (formerly DAGWorks-Inc/burr) — ~2.6k stars, last commit 2026-08 repo fix
Pricing
free (OSS) registry fix
Funding
n/a — donated by DAGWorks to the Apache Software Foundation (Apache Burr, incubating) registry fix
Freshness
2026-10-29 fix
Layer
agent-infra repo fix
Licensing
open-source registry fix
Deployment locus
local repo fix
Platform vs product
platform repo fix
SDK languages
python repo fix
Protocols
opentelemetry vendor fix
Maintainer health
11 issues in 90 days, 36% answered or closed · 2 releases in 12 months (latest 2026-08-29) · bus factor 1 — as of 2026-10-31 repo

When to use

Optimised for: production-grade state-machine LLM workflows with observability

Anti-fit: searched not found

Pros & cons

Pros

State-machine abstraction (vs DAG / ReAct) is genuinely more production-debuggable; companion to Hamilton (popular dataflow framework); strong founder pedigree.

Cons

Smaller stars / ecosystem than LangGraph / CrewAI; commercial sustainability of DAGWorks newer; state-machine framing has learning curve.

Claims & capabilities

OSS BSD-3 state-machine framework; sister project to Hamilton dataflow; founders ex-Stitch Fix / Two Sigma; $4M seed 2023

Technical surface

API surface
searched not found
Backend storage
not applicable — not a memory product
Deployment
Self-hosted only — library + self-hosted tracking UI
Embedding model
not applicable — not a memory product
Multi-tenancy
searched not found
MCP
searched not found
A2A
searched not found
OpenTelemetry
searched not found

Compare Burr (DAGWorks) with…

Alternatives to Burr (DAGWorks) → live options ranked by shared design, licence, hosting and MCP support

Similar systems

Other agent frameworks (no first-party memory layer) in the catalog, ranked by inbound references.

  • Model Context Protocol (MCP spec) T1

    Anthropic-introduced open protocol (Nov 2024) for connecting LLMs to data sources and tools. Donated by Anthropic to the Linux Foundation's Agentic AI Foundation (announced 2025-12-09); now governed as Model Context Protocol, a Series of LF Projects, LLC. Supported across Claude, ChatGPT, VS Code, Cursor and many other clients.

  • LangChain (framework) T1

    Dominant Python/JS framework for LLM apps — tool calling, agents, retrievers, runnables. Memory is one component (LangMem cross-listed); the framework itself is the product.

  • Vercel AI SDK T1

    Vercel's TypeScript LLM SDK — streaming, tool calls, structured outputs, agents. Dominant framework for Next.js LLM apps.

  • LlamaIndex (framework) T1

    Data framework for LLM apps — connectors, indices, query engines, agents, workflows. Memory is one of many subsystems (LlamaIndex Memory cross-listed).

  • OpenAI Agents SDK T1

    OpenAI's official Python framework for agents — handoffs, guardrails, tracing built in. Successor to OpenAI Swarm (experimental); officially supported.

  • LangGraph (orchestration) T1

    LangChain's stateful graph runtime for agents — explicit state, persistence, time-travel debugging, human-in-the-loop. Memory is one persistence target (LangGraph Persistence cross-listed).

Sources (34 cited facts, 0 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-29
    • Homepage “https://github.com/DAGWorks-Inc/burr” → “https://github.com/apache/burr”
    #305
  2. 2026-10-27
    • Model lock-in first recorded as “multi-vendor (BYO)” source
    #275
  3. 2026-10-26
    • License “BSD-3-Clause” → “Apache-2.0” source
    • Latest release first recorded as “v0.43.0 (2026-08-25) — apache-burr” source
    • Pricing first recorded as “free (OSS)” source
    • Funding / ownership first recorded as “n/a — donated by DAGWorks to the Apache Software Foundation (Apache Burr, incubating)” source
    • Deployment first recorded as “Self-hosted only — library + self-hosted tracking UI” source
    #258

Related systems

References (2)

  • LangGraph (orchestration) depends on at runtime — adjacent-infrastructure cell: Hamilton (sister OSS framework, same company); LangGraph (closest competitor); MLflow / Phoenix observability
  • LangGraph Persistence competes with — lightweight alternative to LangGraph.

Referenced by (3)

  • Haystack (framework) integrates with — Haystack integrations directory has a Burr integration page ("Build an agent from Haystack components"). (verified 2026-10-29)
  • MongoDB Atlas Vector Search integrates with — MongoDB's Atlas AI Integrations page lists Burr (DAGWorks) as an integration (some entries are marked community-maintained). (verified 2026-10-29)
  • OpenLLMetry (Traceloop) integrates with — OpenLLMetry's What's Supported page lists Burr (DAGWorks) as instrumented out of the box. (verified 2026-10-29)