LangGraph Persistence

https://docs.langchain.com/oss/python/langgraph/persistence

Distinct from LangMem. Built-in checkpointer saves graph state per super-step (short-term, thread-scoped). Store System adds long-term hierarchical key-value memory across threads with optional vector search + TTL. Postgres / Mongo / Redis stores for production.

At a glance

Type
Checkpoints + Store System
Tier
T2
Created
2024-01 (LangGraph v0.1 released Jan 2024; long-term memory persistence added Oct 2024)
Latest release
not applicable — not OSS
License
not applicable — not OSS
GitHub
not applicable — no GitHub repo
Pricing
OSS free (MIT); LangGraph Platform (now LangSmith Deployment as of Oct 2025): Free Developer plan 100k nodes/mo; Pl…
Funding
$160M total (LangChain parent); $1.2B valuation; Series B Oct 2025

Taxonomy

storage
relational
retrieval
exact-match
persistence
cross-session
update
overwrite
unit
episode
governance
inspectable
conflict
last-write-wins

When to use

Optimised for: durable graph-state checkpointing + Store System for cross-thread memory

Anti-fit: not for non-LangGraph workflows

Pros & cons

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.

Claims & capabilities

Checkpointer saves graph state at every superstep enabling memory between interactions, human-in-the-loop, and fault tolerance. Multiple backends: MemorySaver (in-memory), PostgresSaver, AsyncPostgresSaver, langgraph-checkpoint-redis (Redis integration). Part of LangChain ecosystem ($160M Series B, $1.2B valuation, October 2025)

Technical surface

API surface
SDK: Python, JS/TS
Backend storage
pluggable (Postgres, SQLite, Redis)
Deployment
Both (LangGraph OSS self-hosted; LangSmith Deployment cloud managed or self-hosted)
Embedding model
multiple supported
Multi-tenancy
not applicable — library; namespace is (thread_id, checkpoint_ns); hosted LangGraph Cloud runs in Anthropic-managed VPC
MCP
via official adapter — LangChain MCP adapters
A2A
supported — LangGraph A2A wrappers
OpenTelemetry
first-class — LangSmith + OTel

Compare LangGraph Persistence with…

Similar systems

Other framework-embedded memory in the catalog, ranked by inbound references.

  • AutoGen Memory T2

    ListMemory chronological context + teachable agents that vectorise corrections. Integrates with Mem0/Zep rather than building deep memory natively.

  • CrewAI Memory T2

    Memory subsystem inside the CrewAI orchestration framework; integrates with Mem0 for the long-term tier.

  • AGiXT Adaptive Memory T2

    Open-source AI automation platform. Routes between short-term and long-term memory adaptively across any LLM provider; plugin system for storage backends. Memory managed at the instruction-management layer — task context, instruction state, conversation history as unified agent state.

  • Agno (Phidata) Memory T2

    Agno (formerly Phidata). AgentStorage persists sessions to a DB; AgentMemory auto-classifies/store user preferences and conversation summaries. Single-line integrations with LanceDB, Pinecone, Weaviate, Qdrant.

  • Botpress LLMz T1

    Per-plan vector-DB storage quota + LLMz autonomous engine (in-session working memory) + Knowledge Base (semantic search over uploaded docs). Long-term user memory persists across sessions.

  • DSPy History T3

    dspy.History primitive — typed field holding messages: list[dict] that slots into any Signature . No persistent memory of its own; purely a structured context-injection contract. DSPy's optimisation loop (MIPRO, BootstrapFewShot) treats historical turns as trainable few-shot structure.

Related systems

References (2)

Referenced by (6)

Row last verified 2026-05-14. Catalog data is CC-BY-4.0 — see how to read this.