> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gethaki.space/llms.txt
> Use this file to discover all available pages before exploring further.

# n8n — Community Node

> Two nodes (Haki Context, Haki Capture) for persistent agent memory in n8n workflows — integrations/n8n/n8n-nodes-haki/

`n8n-nodes-haki` gives any n8n AI Agent workflow durable, cross-session
memory on your own Postgres — no vendor lock-in, no per-call memory tax.
Two nodes, placed around your existing AI Agent node: one reads memory
in, one writes the turn back out.

<Info>
  Runs against any Haki instance you already host (`docker compose up`).
  No Haki account required — self-hosted end to end.
</Info>

## Install

```bash theme={null}
# n8n → Settings → Community Nodes → Install
n8n-nodes-haki
```

Or from the CLI, inside your n8n data directory:

```bash theme={null}
npm install n8n-nodes-haki
```

## Credential — Haki API

One credential, shared by both nodes:

<ResponseField name="Base URL" type="string" required>
  The Haki API URL, no trailing slash. From an n8n Docker container to a
  Haki API on the host machine, use
  `http://host.docker.internal:8100` instead of `localhost`.
</ResponseField>

<ResponseField name="API Key" type="string">
  Haki bearer key. Optional in local development (the API runs in open
  mode), required as soon as `HAKI_ADMIN_KEY` or a project key is
  configured server-side.
</ResponseField>

## Haki Context — place before your AI Agent

Fetches the subject's memory as a ready-to-inject block, before the LLM
call.

<ResponseField name="Project ID" type="string" required>
  Haki project (memory scope). Never chosen by the model.
</ResponseField>

<ResponseField name="Subject ID" type="string" required>
  Stable identifier for the person (sessionId, email, webhook ID...).
  Empty or `"default"` is rejected.
</ResponseField>

<ResponseField name="Query" type="string" required>
  The current message — used to rerank relevant facts.
</ResponseField>

<ResponseField name="Budget Tokens" type="number" default="2000">
  Token budget for the returned context packet.
</ResponseField>

<ResponseField name="Purpose" type="string">
  Optional task type (`support`, `onboarding`...), recorded in the trace.
</ResponseField>

Outputs `context_text` (drop straight into your AI Agent's system
message), the raw `packet`, `warnings`, `token_count` and `trace_id`.

## Haki Capture — place after your AI Agent

Records the user/assistant turn once the reply exists.

<ResponseField name="Project ID" type="string" required>
  Must match the Haki Context node.
</ResponseField>

<ResponseField name="Subject ID" type="string" required>
  Reuse the one from the Haki Context node.
</ResponseField>

<ResponseField name="User Message" type="string" required />

<ResponseField name="Assistant Message" type="string" required />

<ResponseField name="Thread ID / Run ID" type="string">
  Optional — either anchors an idempotency key derived from the run/
  thread plus a content hash, so re-running the same n8n execution never
  duplicates the captured turn.
</ResponseField>

<ResponseField name="Wait Consolidation" type="boolean" default="false">
  When on, also calls `/v1/consolidate` so the memory is recallable
  immediately — useful in dev/demo, not needed in steady-state production
  (consolidation runs on its own cadence).
</ResponseField>

<ResponseField name="Origin Trust" type="options" default="trusted">
  `trusted` (direct message from the subject), `semi_trusted` (agent/tool
  output), `third_party` (someone else in the conversation) or
  `untrusted` (ingested content). In a group where the sender is not the
  tracked subject, choose `third_party` — the fact is attributed to that
  third party, never silently merged into the subject's own memory.
</ResponseField>

## A minimal wiring

```
Webhook → Haki Context → AI Agent → Haki Capture → Respond to Webhook
```

`Haki Context` runs first and hands `context_text` to the AI Agent's
system message; `Haki Capture` runs after the agent replies, so the next
turn — even in a brand new execution — starts with everything the agent
already learned.

<Card title="Ready-made workflows" icon="diagram-project" href="https://github.com/GetHaki/Haki/tree/main/integrations/n8n">
  A persistent support-agent template and an end-to-end test workflow
  ship in the repository's `integrations/n8n/` directory — import either
  one directly into n8n to see the wiring above running for real.
</Card>