RecipeAgents / n8n nodes / Simple Memory
Node reference · data pulled Oct 26, 2026n8n Simple Memory node: what the data shows
Gives an AI agent short-term memory of the last few messages in a conversation.
What it does
Formerly Window Buffer Memory. It keeps the most recent exchanges (you set how many) in n8n's own memory, keyed by a session ID, and hands them to the agent on each turn. Nothing is stored in a database, so it suits demos and single-instance setups; Postgres, Redis and other memory nodes persist history properly.
It has the most distinctive partner set of all 22 nodes: chat triggers, agent tools and vector stores. It is almost always part of a chat-bot build.
How often public templates use it
1,086 of the 13,574 public templates on n8n.io (8.0%) contain this node, in the snapshot we took on 2026-10-20. The table splits that by the year each template was published. 2026 runs to October 20.
| Year published | Templates with the node | Share of that year |
|---|---|---|
| 2024 | 34 of 462 | 7.4% |
| 2025 | 774 of 6,564 | 11.8% |
| 2026 | 274 of 5,845 | 4.7% |
The median template using this node has 1,033 views on n8n.io, against 284 for all templates. Template counts show what people publish, not what runs in production.
What it is used with
The most frequent partners are the nodes that appear most often in the same templates. "Lift" compares that with the whole library: 2× means the partner turns up twice as often next to this node as in an average template.
| Most frequent partner | Share of its templates | Lift |
|---|---|---|
| AI Agent | 99.0% | 3.16× |
| OpenAI Chat Model | 62.4% | 2.73× |
| Edit Fields (Set) | 54.0% | 0.97× |
| Chat Trigger | 38.8% | 6.91× |
| Code | 37.4% | 0.63× |
| If | 37.2% | 0.74× |
Strong pairings (in at least 5% of its templates, lift 1.5× or more): 22. The top ones:
| Strong partner | Share of its templates | Lift |
|---|---|---|
| Vector Store Tool | 5.7% | 8.16× |
| HTTP Request Tool | 5.2% | 7.53× |
| Chat Trigger | 38.8% | 6.91× |
| Call n8n Workflow Tool | 12.9% | 6.70× |
| Calculator | 7.6% | 6.17× |
| Pinecone Vector Store | 6.9% | 5.61× |
| MCP Client Tool | 6.4% | 5.56× |
| WhatsApp Trigger | 6.2% | 5.30× |
Most viewed public templates that use it: Ai agent chat (1,847,731 views); Build your first ai agent (1,256,812 views); Building your first whatsapp chatbot (541,254 views).
Versions and changes
Node versions from the npm packages n8n-nodes-base and @n8n/n8n-nodes-langchain, version 2.44.4. New workflows get the default version; workflows built earlier keep the version they were built with until you replace the node.
| Node | Versions | Default | Credential types | Scope |
|---|---|---|---|---|
| Simple Memory | 1, 1.1, 1.2, 1.3, 1.4 | 1.4 | none needed | – |
Source on GitHub: packages/@n8n/nodes-langchain/nodes/memory/MemoryBufferWindow: 22 commits since 2023-11-29, last on 2026-09-16.
Recent fixes and features
- 2026-01-09: fix(Simple Memory Node): Don't allow adding simple memory node if instance in queue or multi-main mode (PR #24083)
Merged dates from GitHub. A fix only helps once your n8n instance runs a release that includes it, so check your version.
Known problems
- Doesn't work in queue mode. With n8n in queue mode, calls may land on different workers, so the memory isn't shared. Since January 2026 n8n blocks adding it on queue or multi-main instances. Source: n8n PR #24083
- Shared memory by accident. Simple Memory nodes in the same workflow share one store unless you give them different session keys. Source: n8n docs
- No session ID. Outside the Chat Trigger there's no session ID by default; map one yourself (for example the Telegram chat ID). Source: n8n docs
- Old node version errors. The AI Agent docs say errors from an outdated Simple Memory are fixed by deleting and re-adding the node. Source: n8n docs
Forum trouble signal: not measured. The n8n community forum's terms forbid automated access, so we don't count forum threads.
Our recipes that use it
1 of our 25 importable workflows uses this node:
Official docs and sources
Usage, pairings, AI share and views: our count of 13,574 public n8n.io templates (snapshot 2026-10-20). Versions: npm packages, version 2.44.4. Changes: n8n's GitHub repository. Docs read and data pulled Oct 26, 2026. We describe each node in our own words; the docs are the authority on settings.
Related nodes
- AI Agent4,246 templates · score 69.9
- OpenAI Chat Model3,104 templates · score 69.6
- Structured Output Parser2,181 templates · score 68.3
- Google Gemini Chat Model1,285 templates · score 65.1
- All 22 nodesSortable table with the scoring method
Questions
- How many n8n templates use the Simple Memory node?
- 1,086 of the 13,574 public templates on n8n.io (8.0%), in our snapshot of 2026-10-20.
- What is the Simple Memory node most often used with?
- AI Agent, which appears in 99.0% of its templates. The most distinctive partner is Vector Store Tool (lift 8.2×).
- Does n8n Simple Memory survive a restart?
- No. It lives in the instance's memory. Use a database-backed memory node for anything that must persist.
- How many messages does it remember?
- As many past exchanges as you set in Context Window Length.