docs: improve OpenClaw integration page (#462)
- Fix tool names to match actual plugin code (honcho_context, honcho_search_conclusions, honcho_search_messages, honcho_ask) - Add link to OpenClaw Honcho Memory docs (docs.openclaw.ai) - Add OpenClaw Memory Docs card in Next Steps - Fix QMD setup: remove manual collection commands, link to OpenClaw QMD docs
This commit is contained in:
Vincent Koc
GitHub
parent
1e0f539fe5
commit
e4873586fa
|
|
@ -11,6 +11,7 @@ sidebarTitle: 'OpenClaw'
|
|||
Honcho can run entirely locally with OpenClaw — no external API required. Keep your data on your machine while getting full memory capabilities across all channels. See the [self-hosting guide](/v3/contributing/self-hosting) to get started.
|
||||
</Note>
|
||||
|
||||
For OpenClaw's own documentation on Honcho, see the [Honcho Memory guide](https://docs.openclaw.ai/concepts/memory-honcho).
|
||||
|
||||
## Install the Plugin
|
||||
|
||||
|
|
@ -67,7 +68,7 @@ Files are uploaded via `session.uploadFile()`. User/owner files go to the owner
|
|||
Once installed, the plugin runs automatically:
|
||||
|
||||
* **Message Observation** — After every AI turn, the conversation is persisted to Honcho. Both user and agent messages are observed, allowing Honcho to build and refine its models.
|
||||
* **Tool-Based Context Access** — The AI can query Honcho mid-conversation using tools like `honcho_recall`, `honcho_search`, and `honcho_analyze` to retrieve relevant context. Context is injected during OpenClaw's `before_prompt_build` phase, ensuring accurate turn boundaries.
|
||||
* **Tool-Based Context Access** — The AI can query Honcho mid-conversation using tools like `honcho_context`, `honcho_search_conclusions`, `honcho_search_messages`, and `honcho_ask` to retrieve relevant context. Context is injected during OpenClaw's `before_prompt_build` phase, ensuring accurate turn boundaries.
|
||||
* **Dual Peer Model** — Honcho maintains separate representations: one for the user (preferences, facts, communication style) and one for the agent (personality, learned behaviors). Each OpenClaw agent gets its own Honcho peer (`agent-{id}`), so multi-agent workspaces maintain isolated memory.
|
||||
* **Clean Persistence** — Platform metadata (conversation info, sender headers, thread context, forwarded messages) is stripped before saving to Honcho, ensuring only meaningful content is persisted.
|
||||
|
||||
|
|
@ -84,17 +85,16 @@ OpenClaw uses a multi-agent architecture where a primary agent can spawn **subag
|
|||
|
||||
| Tool | Description |
|
||||
| ---- | ----------- |
|
||||
| `honcho_session` | Conversation history and summaries from the current session. |
|
||||
| `honcho_profile` | User's peer card — key facts (name, preferences, role). |
|
||||
| `honcho_search` | Semantic search over stored observations. |
|
||||
| `honcho_context` | Full user representation across all sessions. |
|
||||
| `honcho_context` | User knowledge across all sessions. `detail='card'` for key facts, `'full'` for broad representation. |
|
||||
| `honcho_search_conclusions` | Semantic vector search over stored conclusions ranked by relevance. |
|
||||
| `honcho_search_messages` | Find specific messages across all sessions. Filter by sender, date, or metadata. |
|
||||
| `honcho_session` | Current session history and summary. Supports semantic search within the session. |
|
||||
|
||||
### Q&A (LLM-powered)
|
||||
|
||||
| Tool | Description |
|
||||
| ---- | ----------- |
|
||||
| `honcho_recall` | Simple factual question — minimal reasoning. |
|
||||
| `honcho_analyze` | Complex question requiring synthesis — medium reasoning. |
|
||||
| `honcho_ask` | Ask Honcho a question about the user. `depth='quick'` for facts, `'thorough'` for synthesis. |
|
||||
|
||||
## CLI Commands
|
||||
|
||||
|
|
@ -126,32 +126,27 @@ openclaw honcho setup
|
|||
|
||||
## Local File Search (QMD Integration)
|
||||
|
||||
The plugin automatically exposes OpenClaw's `memory_search` and `memory_get` tools when a memory backend is configured, allowing both Honcho cloud memory and local file search together.
|
||||
The plugin automatically exposes OpenClaw's `memory_search` and `memory_get` tools when a [memory backend](https://docs.openclaw.ai/concepts/memory) is configured, allowing both Honcho memory and local file search together.
|
||||
|
||||
### Setup
|
||||
|
||||
1. Install [QMD](https://github.com/tobi/qmd) on your server
|
||||
|
||||
2. Configure OpenClaw in `~/.openclaw/openclaw.json`:
|
||||
2. Configure OpenClaw to use QMD as the memory backend in `~/.openclaw/openclaw.json`:
|
||||
|
||||
```json
|
||||
{
|
||||
"memory": {
|
||||
"backend": "qmd",
|
||||
"qmd": {
|
||||
"limits": {
|
||||
"timeoutMs": 120000
|
||||
}
|
||||
}
|
||||
"backend": "qmd"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
3. Set up QMD collections and restart:
|
||||
OpenClaw manages QMD collections automatically from your workspace memory files and any extra paths in `memory.qmd.paths`. See the [QMD Memory Engine docs](https://docs.openclaw.ai/concepts/memory-qmd) for full setup.
|
||||
|
||||
3. Restart the gateway:
|
||||
|
||||
```bash
|
||||
qmd collection add ~/Documents/notes --name notes
|
||||
qmd update
|
||||
openclaw gateway restart
|
||||
```
|
||||
|
||||
|
|
@ -172,6 +167,10 @@ When QMD is configured, you get both Honcho and local file tools:
|
|||
Source code, issues, and README.
|
||||
</Card>
|
||||
|
||||
<Card title="OpenClaw Memory Docs" icon="book" href="https://docs.openclaw.ai/concepts/memory">
|
||||
Memory backends, search, and configuration in the OpenClaw docs.
|
||||
</Card>
|
||||
|
||||
<Card title="Honcho Architecture" icon="sitemap" href="/v3/documentation/core-concepts/architecture">
|
||||
Learn about peers, sessions, and dialectic reasoning.
|
||||
</Card>
|
||||
|
|
|
|||
Loading…
Reference in New Issue