OpenClaw Quickstart

Get persistent memory running in your OpenClaw gateway in three steps.

Prerequisites

• OpenClaw v2026.3.2 or later
• A Memori API key from app.memorilabs.ai
• An Entity ID to attribute memories to (e.g., a user ID or agent name)

1. Install and Enable

# Install the plugin from npm
openclaw plugins install @memorilabs/openclaw-memori

# Enable it in your workspace
openclaw plugins enable openclaw-memori

# Restart the gateway to load the plugin
openclaw gateway restart

2. Configure

You need two values: your Memori API key and an Entity ID.

Option A: Via CLI (Recommended)

openclaw config set plugins.entries.openclaw-memori.config.apiKey "YOUR_MEMORI_API_KEY"
openclaw config set plugins.entries.openclaw-memori.config.entityId "your-app-user-id"

Option B: Via openclaw.json

Add the following to ~/.openclaw/openclaw.json:

{
  "plugins": {
    "entries": {
      "openclaw-memori": {
        "enabled": true,
        "config": {
          "apiKey": "your-memori-api-key",
          "entityId": "your-app-user-id"
        }
      }
    }
  }
}

Configuration Options

3. Verify

After configuring, restart the gateway and check the logs:

openclaw gateway restart
openclaw gateway logs --filter "[Memori]"

You should see:

[Memori] === INITIALIZING PLUGIN ===
[Memori] Tracking Entity ID: your-app-user-id

Test the Memory Loop

1. Send a message with a preference:

   "I always use TypeScript and prefer functional patterns."

2. Check the logs for a successful augmentation:

   [Memori] === AUGMENTATION HOOK START ===
   [Memori] Capturing conversation turn...
   [Memori] Augmentation successful!
   

   Copy

3. In a new session, ask a question that should trigger recall:

   "Write a hello world script."

4. The agent should recall and apply your TypeScript preference automatically:

   [Memori] === RECALL HOOK START ===
   [Memori] Executing SDK Recall...
   [Memori] Successfully injected memory context.
   

   Copy

What Happens Under the Hood

Once installed, the plugin works automatically on every conversation turn:

No changes to your agent's code or prompts are required. The plugin handles everything through OpenClaw's event lifecycle.