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
- Type
- Pluggable buffer + Postgres/Redis + vector vendor fix
- Tier
- T1
- Section
- Framework-embedded memory
- Created
- 2019-10 (n8n platform launched Oct 2019; AI Agent node added in n8n 1.x era 2023-2024) third-party fix
- Latest release
- n8n@2.44.4 (2026-10-19) repo fix
- License
- Sustainable Use License + n8n Enterprise License (fair-code, source-available; not OSI) repo fix
- GitHub
- n8n-io/n8n — ~208k stars, last release 2026-10 repo fix
- Pricing
- Free self-hosted Community Edition; Cloud: Starter €20/mo; Pro €50/mo; Business $800/mo (40k executions) vendor fix
- Funding
- $253.5M total; Series C $180M Oct 2025 led by Accel (NVentures/Nvidia participating); prior Series B €55M Mar 2025 third-party fix
- Freshness
- 2026-10-22 fix
- Layer
- agent-infra repo fix
- Licensing
- commercial repo fix
- Compliance
- gdpr, soc3 vendor fix
- Developer activity
- OpenRank 165.47 (12-mo avg 211.38) · 477 participants — 2026-09 third-party 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…
Alternatives to n8n AI Agent Memory → live options ranked by shared design, licence, hosting and MCP support
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 it is Pluggable buffer + Postgres/Redis + vector vendor
- What it does & what's distinct Low-code workflow platform. AI Agent node ships with pluggable memory sub-graph: Simple … vendor
- Claims / benefits Free self-hosted (Community Edition); Cloud from €24/mo. vendor
- Modalities text (workflow automation; no native multimodal memory — image/audio inputs processed vi… vendor
- Created 2019-10 (n8n platform launched Oct 2019; AI Agent node added in n8n 1.x era 2023-2024) third-party
- Latest release n8n@2.44.4 (2026-10-19) repo
- License Sustainable Use License + n8n Enterprise License (fair-code, source-available; not OSI) repo
- GitHub n8n-io/n8n — ~208k stars, last release 2026-10 repo
- Funding $253.5M total; Series C $180M Oct 2025 led by Accel (NVentures/Nvidia participating); pr… third-party
- Customers / scale 51-200 ppl Free self-hosted, paid cloud, customer names not disclosed vendor
- Pricing Free self-hosted Community Edition; Cloud: Starter €20/mo; Pro €50/mo; Business $800/mo … vendor
- Compliance SOC 2 Type II (n8n 2.0, Dec 2025); GDPR compliant; self-hosted for data sovereignty in h… vendor
- Data handling Self-hosted: all data on your infrastructure; Cloud: data handled per n8n DPA vendor
- Deployment Self-hosted (Docker / npm); cloud via n8n.cloud SaaS vendor
- HQ Germany (Berlin) vendor
- Founders / pedigree n8n (Berlin-based workflow automation); founder Jan Oberhauser vendor
- Memory volume / scale no scale claim (n8n platform: 100k+ self-hosted installs; memory sub-feature share not t… vendor
- Versioning immutable append-log vendor
- Tombstoning append-only no delete vendor
- Schema evolution schema with migration vendor
- Namespace primitives per-tenant vendor
- Contradiction handling always append (no resolution) vendor
- Forgetting policy none (permanent) vendor
- MCP support via official adapter — n8n MCP node vendor
- OTel via adapter — Langfuse / OTel community vendor
- Webhooks / events webhooks supported (core feature) vendor
- Import / export JSON workflow export vendor
- Integration count 0 vendor
- Orchestration hybrid (workflow-driven; AI Agent node memory + external store nodes) vendor
- Programmatic control declarative config (workflow nodes) vendor
- Pricing specifics per-execution: free self-hosted Community Edition; Cloud Starter €20/mo; Pro €50/mo; Bus… vendor
- Agent abstraction DAG (workflow) vendor
- Memory primitives multiple (Simple/Postgres/Redis + Qdrant/Pinecone/MongoDB) vendor
- LLM lock any (BYO via LLM nodes) vendor
- Runtimes Node/TypeScript runtime; declarative cross-language repo
- Session handling sticky session (per workflow execution) vendor
- Validated verticals automation engineers, internal IT, contact center, KM vendor
- Time to running <1hr (n8n self-host or cloud) vendor
- Anti-fit not for code-first agent stacks (low-code workflow positioning) vendor
- Optimised for low-code workflow + pluggable memory vendor
- Adjacent infrastructure requires n8n; BYO LLM + Postgres/Redis/vector vendor
- Pros n8n's workflow-orchestration backbone gives agents memory tied to durable workflow state… vendor
- Cons Memory features are still maturing relative to dedicated memory layers; thin documentati… vendor
- Project & sources memory docs vendor
- architecture-deployment-locus hybrid vendor
- licensing-bucket commercial repo
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup agent-infra repo
- developer-activity-opendigger {"activity":1677.48,"as_of":"2026-09","openrank_12mo":211.38,"openrank_current":165.47,"… third-party
- compliance-certifications gdpr,soc3 vendor
- sdk-languages rest vendor
- maturity ga third-party
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 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
- 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
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)