n8n AI Agent Memory

https://docs.n8n.io/advanced-ai/examples/understand-memory/

Low-code workflow platform. AI Agent node ships with pluggable memory sub-graph: Simple Memory for development; Postgres/Redis for production; vector store nodes (Qdrant, Pinecone, MongoDB Atlas) for semantic recall.

Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 53 cited facts, 4 with a third-party source · 2 recorded changes · Suggest a correction

At a glance

Tier
T1
Latest release
n8n@2.44.4 (2026-10-19) repo fix
Freshness
2026-10-22 fix
Layer
agent-infra repo fix
Licensing
commercial repo fix
Deployment locus
hybrid vendor fix
Platform vs product
platform vendor fix
Maturity
ga third-party fix
SDK languages
rest vendor fix
Compliance
gdpr, soc3 vendor fix

Memory taxonomy

storage
vector
retrieval
similarity
persistence
cross-session
update
append-only
unit
episode
governance
inspectable
conflict
append-only

When to use

Optimised for: low-code workflow + pluggable memory

Anti-fit: not for code-first agent stacks (low-code workflow positioning)

Pros & cons

Pros

n8n's workflow-orchestration backbone gives agents memory tied to durable workflow state — not just chat history.

Cons

Memory features are still maturing relative to dedicated memory layers; thin documentation on eviction policy.

Claims & capabilities

Free self-hosted (Community Edition); Cloud from €24/mo.

Technical surface

API surface
searched not found
Backend storage
searched not found
Deployment
Self-hosted (Docker / npm); cloud via n8n.cloud SaaS
Embedding model
searched not found
Multi-tenancy
searched not found
MCP
via official adapter — n8n MCP node
A2A
searched not found
OpenTelemetry
via adapter — Langfuse / OTel community

Compare n8n AI Agent Memory with…

Similar systems

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

  • Spring AI ChatMemory T3

    Wraps conversation memory behind an Advisor abstraction. MessageWindowChatMemory default 20-msg sliding window (preserves system messages); pluggable ChatMemoryRepository backends (in-memory, JDBC, Cassandra, Neo4j). Memory injected as cross-cutting concern at the ChatClient level.

  • Flowise Memory T1

    Discontinued: Flowise (acquired by Workday, Aug 2025) was sunset in 2026 — code freeze 2026-07-29, GitHub repo archived 2026-08-13, end of life 2026-08-31. Was a visual LangChain canvas with LangChain-native memory nodes (Buffer, Buffer Window, Conversation Summary Buffer) backed by an internal chat_message DB table; Buffer Window kept the last K interactions, Summary Buffer compressed older turns while keeping recent ones verbatim.

  • LangGraph Persistence T2

    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.

  • AutoGen Memory T2

    AutoGen's memory layer: ListMemory chronological context plus teachable agents that vectorise corrections; integrates with Mem0/Zep rather than building deep memory natively. Microsoft AutoGen is in maintenance mode (community managed, bug and security fixes only), and Microsoft points new projects to Microsoft Agent Framework.

  • CrewAI Memory T2

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

  • Hermes Agent memory (Nous Research) T3

    Nous Research's open-source self-improving agent keeps an agent-curated MEMORY.md/USER.md notebook injected at session start, full-text (FTS5) search over past sessions that returns raw messages without LLM summarisation, and optional Honcho user modelling. one of the most-starred agent projects of 2026.

Sources (52 cited facts, 4 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. 2026-10-23
    • Pricing “Free self-hosted Community Edition; Cloud: Starter €20/mo; Pro €50/mo; Business $800/mo (40k executions); Enterpris…” → “Free self-hosted Community Edition; Cloud: Starter €20/mo; Pro €50/mo; Business $800/mo (40k executions)” source
    • Funding / ownership “$253.5M total; Series C $180M Oct 2025 led by Accel (NVentures/Nvidia participating); prior Series B €55M Mar 2025 …” → “$253.5M total; Series C $180M Oct 2025 led by Accel (NVentures/Nvidia participating); prior Series B €55M Mar 2025” source
    #223
  2. 2026-10-22
    • License “not applicable — not OSS” → “Sustainable Use License + n8n Enterprise License (fair-code, source-available; not OSI)” source
    • Latest release “not applicable — not OSS” → “n8n@2.44.4 (2026-10-19)” source
    #195

Related systems

References (4)

  • MongoDB Atlas Vector Search integrates with — vector store nodes (Qdrant, Pinecone, MongoDB Atlas) for semantic recall
  • Pinecone integrates with — vector store nodes (Qdrant, Pinecone, MongoDB Atlas) for semantic recall
  • Qdrant integrates with — vector store nodes (Qdrant, Pinecone, MongoDB Atlas) for semantic recall
  • Zep & Graphiti integrates with — n8n built-in memory sub-node: Zep memory node. (verified 2026-10-29)