loom-openclaw-plugin/) that integrates Loom as a Context Engine, providing structured long-term memory for OpenClaw.
Quick Start
1. Install & configure Loom
configs/loom.yaml and fill in the llm section (or copy .env.example to .env and edit):
2. Start the Loom backend
http://localhost:8666 by default. Use loom serve status to verify.
3. Install the plugin
If you don’t have OpenClaw yet, see the OpenClaw Install Guide first.
4. Start (or restart) the Gateway
If the Gateway is not running, start it:5. Verify
/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
/loomcommand suite for manual memory management
Configuration
Configure inopenclaw.json under plugins.entries.loom-claw.config:
Example
openclaw.json:
Slash Commands
View & Recall
Memory Management
Schema Files
Template Management
Configuration
Creating Custom Templates via Slash Command
Create templates directly from the chat using the compact text format:- First line:
template_name description(name allows letters, numbers,_,-) - Following lines:
domain_name: field1 | description, field2 | description
/loom templates create --json {"_meta":{"name":"..."},...}
Agent Tools
Five tools are registered for the OpenClaw agent:Context Engine Lifecycle
Data Flow
Data Storage
Loom stores data under the OpenClaw Agent Workspace:configs/loom.yaml: