Burr (DAGWorks) vs LangGraph Persistence

Burr (DAGWorks) (agent frameworks (no first-party memory layer)) vs LangGraph Persistence (framework-embedded memory): cross-category comparison covering architecture, taxonomy, license, pricing, and direct edges.

Burr (DAGWorks) · LangGraph Persistence

How they relate

  • Burr (DAGWorks) competes with LangGraph Persistence — itions; lightweight alternative to LangGraph.

Cost & capability

Burr (DAGWorks)LangGraph Persistence
Capability bandcompetentcompetent
Capability composite5572
Cost tiersearched not foundfree
$/Mtok inputsearched not found0
$/Mtok outputsearched not found0
Use casesScoped Agentic, Long Running SessionLong Running Session, Multi Agent Coordination, Scoped Agentic, Memory Augmented Chat

Where they differ (18)

Rows where both sides have data and the values disagree — the shortlist of dimensions that actually distinguish these two systems.

Burr (DAGWorks)LangGraph Persistence
Capability composite5572
Cost tiersearched not foundfree
$/Mtok inputsearched not found0
$/Mtok outputsearched not found0
Use casesScoped Agentic, Long Running SessionLong Running Session, Multi Agent Coordination, Scoped Agentic, Memory Augmented Chat
SectionAgent frameworks (no first-party memory layer)Framework-embedded memory
TierT3T2
TypeState-machine agent frameworkCheckpoints + Store System
Created20242024-01 (LangGraph v0.1 released Jan 2024; long-term memory persistence added Oct 2024)
Pricingsearched not foundOSS free (MIT); LangGraph Platform (now LangSmith Deployment as of Oct 2025): Free Developer plan 100k nodes/mo; Pl…
Fundingsearched not found$160M total (LangChain parent); $1.2B valuation; Series B Oct 2025
Deploymentsearched not foundBoth (LangGraph OSS self-hosted; LangSmith Deployment cloud managed or self-hosted)
API surfacesearched not foundSDK: Python, JS/TS
MCPsearched not foundvia official adapter — LangChain MCP adapters
A2Asearched not foundsupported — LangGraph A2A wrappers
OpenTelemetrysearched not foundfirst-class — LangSmith + OTel
Optimised forsearched not founddurable graph-state checkpointing + Store System for cross-thread memory
Anti-fitsearched not foundnot for non-LangGraph workflows

At a glance

Burr (DAGWorks)LangGraph Persistence
SectionAgent frameworks (no first-party memory layer) Framework-embedded memory
TierT3 T2
TypeState-machine agent framework Checkpoints + Store System
Created2024 2024-01 (LangGraph v0.1 released Jan 2024; long-term memory persistence added Oct 2024)
Latest releasesearched not found
LicenseBSD-3-Clause
GitHubsearched not found
Pricingsearched not found OSS free (MIT); LangGraph Platform (now LangSmith Deployment as of Oct 2025): Free Developer plan 100k nodes/mo; Pl…
Fundingsearched not found $160M total (LangChain parent); $1.2B valuation; Series B Oct 2025
Backend storage pluggable (Postgres, SQLite, Redis)
Deploymentsearched not found Both (LangGraph OSS self-hosted; LangSmith Deployment cloud managed or self-hosted)
API surfacesearched not found SDK: Python, JS/TS
Embedding multiple supported
Multi-tenancysearched not found
MCPsearched not found via official adapter — LangChain MCP adapters
A2Asearched not found supported — LangGraph A2A wrappers
OpenTelemetrysearched not found first-class — LangSmith + OTel
Optimised forsearched not found durable graph-state checkpointing + Store System for cross-thread memory
Anti-fitsearched not found not for non-LangGraph workflows

Taxonomy

AxisBurr (DAGWorks)LangGraph Persistence
storagen/arelational
retrievaln/aexact-match
persistencen/across-session
updaten/aoverwrite
unitn/aepisode
governancen/ainspectable
conflictn/alast-write-wins

Pros & cons

Burr (DAGWorks)

Pros: searched not found

Cons: searched not found

LangGraph Persistence

Pros: Persistent state for graph agents — checkpointing and resumability are first-class, not bolted on.

Cons: LangGraph-shaped; persistence model is general but most idiomatic when paired with LangChain memory.

Rows last verified 2026-05-14 / 2026-05-14. Data is CC-BY-4.0 — see how to read this.