Documentation Index
Fetch the complete documentation index at: https://docs.loom.teamecho.ai/llms.txt
Use this file to discover all available pages before exploring further.
Loom includes a first-party OpenClaw plugin (loom-openclaw-plugin/) that integrates Loom as a Context Engine, providing structured long-term memory for OpenClaw.
Quick Start
cd Loom
pip install -e .
loom init # generates configs/loom.yaml and template files
configs/loom.yaml and fill in the llm section (or copy .env.example to .env and edit):
# configs/loom.yaml
llm:
api_key: "your-api-key"
model: "google/gemini-2.5-flash" # any OpenAI-compatible model
base_url: "https://openrouter.ai/api/v1" # OpenRouter / OpenAI / local endpoint
2. Start the Loom backend
loom serve # foreground (Ctrl+C to stop)
# or
loom serve start # background daemon (recommended)
http://localhost:8666 by default. Use loom serve status to verify.
3. Install the plugin
clawhub login
openclaw plugins install loom-claw
openclaw plugins install --link /path/to/Loom/loom-openclaw-plugin
4. Start (or restart) the Gateway
If the Gateway is not running, start it:
If the Gateway is already running, restart it to load the new plugin:
5. Verify
openclaw plugins list --enabled # plugin should appear
openclaw plugins inspect loom-claw # detailed plugin info
openclaw gateway status # Gateway health check
/loom status to confirm end-to-end connectivity. The plugin will automatically extract and recall structured memories each turn.
Features
- Auto-extract and auto-recall — extracts information into structured schemas and injects it into the system prompt each turn
- Schema-based memory — organizes knowledge into typed domains and fields
- Multi-schema management — create, switch, backup, and restore independent schema files
- Template system — bootstrap schemas from built-in, shared, or custom templates; full template CRUD via slash commands
- Agent tools — 5 registered tools for LLM-driven memory management
- Slash commands — full
/loom command suite for manual memory management
Configuration
Configure in openclaw.json under plugins.entries.loom-claw.config:
| Option | Default | Description |
|---|
loomBaseUrl | http://localhost:8666 | Loom backend URL |
sessionId | default | Loom session ID |
schemaId | default | Shared schema file ID |
schemaTemplate | — | Initial template |
buildEveryNTurns | 1 | Extraction frequency (same as Loom build_every_n_turns) |
openclaw.json:
{
"plugins": {
"entries": {
"loom-claw": {
"enabled": true,
"config": {
"loomBaseUrl": "http://localhost:8666",
"sessionId": "default",
"schemaId": "default",
"schemaTemplate": "general",
"buildEveryNTurns": 1
}
}
}
}
}
Slash Commands
View & Recall
| Command | Description |
|---|
/loom or /loom status | Show connection status and schema overview |
/loom inspect | View schema structure with field values |
/loom recall | Recall all stored memory data |
| Command | Description |
|---|
/loom forget <domain> | Delete a specific schema domain |
/loom forget --all | Clear all memory |
/loom reset | Backup current schema and start fresh |
| Command | Description |
|---|
/loom schemas | List all schema files and backups |
/loom new [name] | Create a new blank schema and switch to it |
/loom switch <schema_id> | Switch to an existing schema |
/loom restore <backup_id> | Restore a schema from backup |
| Command | Description |
|---|
/loom templates | List all available templates (grouped by source) |
/loom templates show <name> | Preview template domains and fields |
/loom templates use <name> | Create a schema from template and switch to it |
/loom templates create | Show format help for creating custom templates |
/loom templates create <definition> | Create a custom template (compact text or --json) |
/loom templates delete <name> | Delete a custom template |
/loom templates help | Show template command help |
| Command | Description |
|---|
/loom config | View current runtime configuration |
/loom config buildEveryNTurns <N> | Update extraction frequency |
/loom help | Show help |
Creating Custom Templates via Slash Command
Create templates directly from the chat using the compact text format:
/loom templates create game_character
character: name, class, level, skills
story: main_quest, side_quests
social: friends, guild, reputation
- First line:
template_name description (name allows letters, numbers, _, -)
- Following lines:
domain_name: field1 | description, field2 | description
Or use JSON format: /loom templates create --json {"_meta":{"name":"..."},...}
Five tools are registered for the OpenClaw agent:
| Tool | Description |
|---|
loom_inspect | Inspect schema structure and field values |
loom_recall | Recall all schema memory data |
loom_build | Manually trigger information extraction |
loom_forget | Delete a domain or clear all memory |
loom_update | Trigger schema update from chat history |
Context Engine Lifecycle
| OpenClaw Hook | Plugin Behavior | Loom API |
|---|
bootstrap | Verify backend, create session, load template | POST /api/sessions, GET /api/schemas/recall-all |
assemble | Fetch schema data, inject into system prompt | GET /api/schemas/recall-all |
afterTurn | Format messages, extract info | POST /api/build |
compact | Delegate to runtime | — |
Data Flow
User message → OpenClaw agent
↓
[assemble] → GET /api/schemas/recall-all
↓ → schema data injected into system prompt
Model generates response
↓
[afterTurn] → POST /api/build
→ CM Agent extracts information
→ Updates schema
→ Available on next assemble
Data Storage
Loom stores data under the OpenClaw Agent Workspace:
~/.openclaw/workspace/loom/
├── schemas/ # Schema files (shared across sessions)
│ ├── default.json
│ └── backups/
│ └── default_20260314_180736.json
└── sessions/
└── default.json
configs/loom.yaml:
persistence:
session_dir: "~/.openclaw/workspace/loom/sessions"
schemas_dir: "~/.openclaw/workspace/loom/schemas"
