Login

Integration

Long-term memory for n8n workflows

n8n is the no-code automation platform, where every workflow is a chain of nodes. AI workflows in n8n have no built-in long-term memory. `n8n-nodes-engram` is a community node with six operations (Store, Query, List, Delete, Clear, List Buckets) plus the `usableAsTool` flag, so n8n's AI Agent nodes can call them directly.

Get an API key (free) All integrations →

Install

Three steps: sign up for an Engram API key, paste a BYOK LLM-provider key on /models, then drop the snippet below into n8n.

Three steps to memory in your agent

  1. Sign up. Free, no card. You'll land on a Getting Started page that walks the next two steps.
  2. Add your LLM key. Engram is BYOK. Paste an OpenAI / Anthropic / Groq / Together / Fireworks key and we'll route every extraction and query call through your provider. You pay your provider directly. We never see your inference.
  3. Paste the snippet below into your agent and restart it. Use Authorization: Bearer <api-key>with the API key from your portal.

n8n-nodes-engram: n8n community node

Six operations against Engram's REST API: Store / Query / List Memories / List Buckets / Delete Memory / Clear Memories. The node is usableAsTool, so n8n's AI Agent nodes can call it directly. Source: github.com/lumetra-io/engram-n8n-nodes.

  1. In n8n: Settings → Community Nodes → Install. Enter n8n-nodes-engram and confirm. (Self-hosted n8n needs N8N_COMMUNITY_PACKAGES_ENABLED=true.)
  2. Create an Engram API credential: paste your eng_live_… key, leave Base URL at https://api.lumetra.io for Lumetra Cloud (or override for self-hosted Engram). The credential's Test button calls GET /v1/buckets?limit=1 to verify.
  3. Drag the Engram node into any workflow. To use as an AI tool, drag it onto an AI Agent node's tools panel; the six operations become callable from the agent's reasoning.

What you can do once memory's wired in

  • Build a customer-support workflow where the AI Agent recalls past tickets via `engram_query_memory`
  • Auto-archive Slack messages or emails to Engram with a scheduled n8n workflow
  • Multi-step pipeline: extract structured facts with the AI node, store with the Engram node, query later
  • Add Engram to existing n8n workflows alongside Notion, Airtable, or your CRM with no code, just nodes

FAQ

Does this work on n8n Cloud and self-hosted?

Self-hosted: yes. Set `N8N_COMMUNITY_PACKAGES_ENABLED=true` and (to use the node as an AI Agent tool) also `N8N_COMMUNITY_PACKAGES_ALLOW_TOOL_USAGE=true`. n8n Cloud only allows *verified* community packages, and `n8n-nodes-engram` isn't verified yet, so until it lands in n8n's verified-nodes list the Cloud path is unavailable and you'll need a self-hosted instance.

Where do I configure the API key?

Settings → Credentials → New → Engram API. The credential's Test button calls `GET /v1/buckets?limit=1` to verify the key, giving you instant feedback before it goes into a workflow.

Can the AI Agent node call Engram tools directly?

Yes. The node is `usableAsTool`: drag it into the AI Agent's tools panel and the model can call Store, Query, or List as part of its reasoning.

Related integrations

Dify Open-source LLM app platform. Lumetra-maintained plugin (lumetra/engram) with six native tools and bearer-key auth. Marketplace listing is pending; install via the GitHub repo as a local plugin today. Read more → Paperclip Auto-archives every issue, agent run, and approval into Engram with no agent code or LLM tool calls. Read more → AstrBot Multi-platform chatbot framework. Adds /remember and /recall slash commands, plus optional auto-archive of every message. Read more →

Ship durable memory in n8n today

Free tier: 10K memories and 50K retrievals per month. No credit card. Same Engram backend powers all 41 integrations, so memories you write from one client are immediately queryable from the rest.

Start free See pricing