fix: updating docs based on new clawhub skill (#381)
This commit is contained in:
ajspig
GitHub
parent
f330cce386
commit
f6e1f237e2
|
|
@ -22,23 +22,78 @@ echo "HONCHO_API_KEY=hc_..." >> ~/.openclaw/.env
|
|||
|
||||
## Install the Plugin
|
||||
|
||||
### Option A: ClawHub Skill (Recommended)
|
||||
|
||||
The `honcho-setup` skill on [ClawHub](https://clawhub.ai/ajspig/honcho-setup) handles installation, migration, and workspace setup interactively:
|
||||
|
||||
```bash
|
||||
clawhub install honcho-setup
|
||||
```
|
||||
|
||||
Then run the skill from a chat session. It will walk you through plugin installation, legacy memory migration, and workspace doc setup.
|
||||
|
||||
### Option B: Manual Install
|
||||
|
||||
Install the plugin using the OpenClaw plugin system. **Do not install `@honcho-ai/sdk` directly or use `npm install` in the workspace.**
|
||||
|
||||
```bash
|
||||
openclaw plugins install @honcho-ai/openclaw-honcho
|
||||
```
|
||||
|
||||
The install script automatically syncs workspace docs, migrates existing memory to Honcho, and archives legacy files. Restart the gateway after installing:
|
||||
Then enable it:
|
||||
|
||||
```bash
|
||||
openclaw plugins enable openclaw-honcho
|
||||
```
|
||||
|
||||
If the gateway logs show `Cannot find module '@honcho-ai/sdk'`, install the plugin's dependencies manually:
|
||||
|
||||
```bash
|
||||
cd ~/.openclaw/extensions/openclaw-honcho && npm install
|
||||
```
|
||||
|
||||
Restart the gateway after installing:
|
||||
|
||||
```bash
|
||||
openclaw gateway restart
|
||||
```
|
||||
|
||||
## Migrating Legacy Memory
|
||||
|
||||
If you have existing workspace memory files (`USER.md`, `MEMORY.md`, `IDENTITY.md`, `memory/`, `canvas/`, etc.), these can be migrated to Honcho. The recommended path is the `honcho-setup` ClawHub skill, which handles this interactively.
|
||||
|
||||
<Note>
|
||||
Commit any existing memory files to version control before migrating.
|
||||
</Note>
|
||||
|
||||
### Legacy files
|
||||
|
||||
**User/owner files** (content describes the user):
|
||||
- `USER.md`, `IDENTITY.md`, `MEMORY.md`
|
||||
- All files in `memory/` and `canvas/` directories
|
||||
|
||||
**Agent/self files** (content describes the agent):
|
||||
- `SOUL.md`, `AGENTS.md`, `TOOLS.md`, `BOOTSTRAP.md`, `HEARTBEAT.md`
|
||||
|
||||
### Upload to Honcho
|
||||
|
||||
Files are uploaded to Honcho via the **messages upload endpoint**. User/owner files are uploaded through the owner peer, and agent/self files through the openclaw peer. The `honcho-setup` skill automates this using `session.uploadFile()`.
|
||||
|
||||
### Archive originals
|
||||
|
||||
After uploading:
|
||||
|
||||
1. **Remove originals** for legacy-only files: `USER.md`, `MEMORY.md`, `IDENTITY.md`, `HEARTBEAT.md`
|
||||
2. **Keep originals** for active workspace docs: `AGENTS.md`, `TOOLS.md`, `SOUL.md`, `BOOTSTRAP.md`
|
||||
3. **Move directories** (`memory/`, `canvas/`) into an `archive/` directory
|
||||
|
||||
## How It Works
|
||||
|
||||
Once installed, the plugin runs automatically:
|
||||
|
||||
* **Context Injection** — Before every AI turn, Honcho injects the user's profile, representation, and conversation summary.
|
||||
* **Message Observation** — After every AI turn, the exchange is persisted to Honcho for extraction and long-term storage.
|
||||
* **Dual Peer Model** — Honcho maintains separate representations for the user and the agent.
|
||||
* **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.
|
||||
* **Dual Peer Model** — Honcho maintains separate representations: one for the user (preferences, facts, communication style) and one for the agent (personality, learned behaviors).
|
||||
|
||||
## AI Tools
|
||||
|
||||
|
|
@ -77,12 +132,53 @@ Optional — the plugin works out of the box with `HONCHO_API_KEY` set.
|
|||
|
||||
### Self-Hosted Honcho
|
||||
|
||||
Point the plugin to your local instance:
|
||||
Point the plugin to your local instance and follow the [self-hosting guide](https://github.com/plastic-labs/honcho?tab=readme-ov-file#local-development) to get started:
|
||||
|
||||
```bash
|
||||
echo "HONCHO_BASE_URL=http://localhost:8000" >> ~/.openclaw/.env
|
||||
```
|
||||
|
||||
## 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.
|
||||
|
||||
### Setup
|
||||
|
||||
1. Install [QMD](https://github.com/tobi/qmd) on your server
|
||||
|
||||
2. Configure OpenClaw in `~/.openclaw/openclaw.json`:
|
||||
|
||||
```json
|
||||
{
|
||||
"memory": {
|
||||
"backend": "qmd",
|
||||
"qmd": {
|
||||
"limits": {
|
||||
"timeoutMs": 120000
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
3. Set up QMD collections and restart:
|
||||
|
||||
```bash
|
||||
qmd collection add ~/Documents/notes --name notes
|
||||
qmd update
|
||||
openclaw gateway restart
|
||||
```
|
||||
|
||||
### Available Tools
|
||||
|
||||
When QMD is configured, you get both Honcho and local file tools:
|
||||
|
||||
| Tool | Source | Description |
|
||||
| ---- | ------ | ----------- |
|
||||
| `honcho_*` | Honcho | Cross-session memory, user modeling, dialectic reasoning |
|
||||
| `memory_search` | QMD | Search local markdown files |
|
||||
| `memory_get` | QMD | Retrieve file content |
|
||||
|
||||
## Next Steps
|
||||
|
||||
<CardGroup cols={2}>
|
||||
|
|
|
|||
Loading…
Reference in New Issue