Memori

Memori - Structured Long-term Memory for OpenClaw

Give your OpenClaw agents a persistent, structured memory system. Memori automatically captures what happens in the background and gives agents the tools to bring it back when relevant.

Core Workflow

Memori operates on two parallel tracks through OpenClaw lifecycle hooks:

1. Automatic Capture (Advanced Augmentation)

After the agent responds, Memori automatically:

1. Captures the conversation turn (user + assistant) 2. Sends it to the Memori backend for intelligent processing 3. Extracts durable facts, deduplicates, and updates the knowledge graph. _(No manual save commands needed - capture just works)._

2. Agent-Controlled Recall (Intelligent Retrieval)

Memori does not blindly stuff the context window. Instead, it equips the agent with explicit tools to retrieve history exactly when it needs it:

1. memori_recall: Searches the structured memory graph for specific facts, constraints, and prior decisions. 2. memori_recall_summary: Retrieves structured daily briefs and rolling summaries of prior sessions. 3. memori_feedback: Reports on memory quality to improve extraction accuracy.

Installation

openclaw plugins install @memorilabs/openclaw-memori

Configuration

Add to your ~/.openclaw/openclaw.json or use the openclaw memori init CLI command:

openclaw memori init \
  --api-key "YOUR_MEMORI_API_KEY" \
  --entity-id "your-entity-id" \
  --project-id "your-project-id"

Alternatively, configure it directly via JSON:

{
  "plugins": {
    "entries": {
      "openclaw-memori": {
        "enabled": true,
        "config": {
          "apiKey": "${MEMORI_API_KEY}",
          "entityId": "openclaw-user",
          "projectId": "default-project"
        }
      }
    }
  }
}

Configuration Options

Agent Instructions & Skill Rules

When this plugin is active, the OpenClaw agent is bound by the following strict behavioral rules injected into its system prompt:

Verification

Check that the plugin is working:

# Verify plugin is securely connected to the API
openclaw memori status --check
Check for Memori logs in gateway output
openclaw gateway logs --filter "[Memori]"

Quota Management

Check your current API quota:

memori quota

Example output:

 __  __                           _
|  \/  | ___ _ __ ___   ___  _ __(_)
| |\/| |/ _ \ '_  _ \ / _ \| '__| |
| |  | |  __/ | | | | | (_) | |  | |
|_|  |_|\___|_| |_| |_|\___/|_|  |_|
                  perfectam memoriam
                       memorilabs.ai
+ Maximum # of Memories: 100
+ Current # of Memories: 0
+ You are not currently over quota.

Use this to monitor usage and upgrade if needed.

Performance

All storage is handled by the Memori backend and is scoped safely alongside your local MEMORY.md file without overwriting it.

Troubleshooting

Plugin not loading:

No memories captured:

Memories not recalled:

Quota exceeded:

Learn More

Notes

This skill teaches the agent about the Memori plugin. The plugin must be installed separately via npm. Once installed, memory capture happens automatically in the background, and the agent is empowered to explicitly query its memories when needed.

Add to your ~/.openclaw/openclaw.json or use the openclaw memori init CLI command:

openclaw memori init \
  --api-key "YOUR_MEMORI_API_KEY" \
  --entity-id "your-entity-id" \
  --project-id "your-project-id"

Alternatively, configure it directly via JSON:

{
  "plugins": {
    "entries": {
      "openclaw-memori": {
        "enabled": true,
        "config": {
          "apiKey": "${MEMORI_API_KEY}",
          "entityId": "openclaw-user",
          "projectId": "default-project"
        }
      }
    }
  }
}

Configuration Options

This skill teaches the agent about the Memori plugin. The plugin must be installed separately via npm. Once installed, memory capture happens automatically in the background, and the agent is empowered to explicitly query its memories when needed.