Quick Start

Give OpenClaw 🦞 persistent memory. Your AI remembers every conversation, every decision, every file — across every session.

Quick Start (under a minute)

Step 1: Install the plugin

openclaw plugins install mr-memory

Step 2: Add your memory key

openclaw mr <your-memory-key>

Step 3: Upload your existing history

openclaw mr upload

Run this once. It automatically finds your conversation history and workspace files and uploads everything to your memory vault. Your AI wakes up already knowing everything you've ever talked about.

From here, everything stays in sync automatically. You never need to run upload again unless you want a fresh start.

Get your free memory key at app.memoryrouter.ai.

How Your Memory Stays in Sync

After the initial upload, MemoryRouter keeps everything current automatically:

New conversations are stored automatically after each AI response — that's separate from file sync.

Sync is debounced at 60 seconds — if startup sync just ran, the first session won't re-sync. But if you edit a file 2 minutes later and start a new session, it catches it.

Smart hash manifest — only files that actually changed get updated. No rebuilding the entire index every time.

Starting fresh

If you ever need to nuke your vault and rebuild from scratch:

openclaw mr delete    # Clear the vault
openclaw mr upload    # Rebuild from your current workspace + sessions

How It Works

User → OpenClaw (+ relevant memories injected locally) → Provider → Response

MemoryRouter replaces OpenClaw's built-in memory with persistent, sub-100ms cloud memory. When you chat, it retrieves relevant memories and injects them into the system prompt. When the AI responds, it stores new memories automatically. Your workspace files stay in sync — only what changed gets updated, so it's always fast.

Relay, not proxy. MemoryRouter offers a universal proxy for any platform, but the OpenClaw plugin was rebuilt from the ground up as a relay — a community-requested redesign. Memories are retrieved and injected locally inside OpenClaw. Your API keys, your inference, your data — none of it touches our servers. We only store and retrieve memories.

openclaw mr off restores everything to stock — built-in memory, workspace indexing, all defaults.

What Makes It Faster

OpenClaw's built-in memory rebuilds the vector index on every search. The more files you have, the longer that takes — often 30-60 seconds per response.

MemoryRouter retrieves your memories in under 100ms and injects them before the model even starts. Same model, same prompt — responses go from 30-60 seconds down to 2-3 seconds. We call it OpenClaw Instant.

Cron Jobs & Scheduled Tasks

Without MemoryRouter, your cron jobs and scheduled tasks run with zero context. With MemoryRouter, they remember everything you've ever discussed. Your morning email triage knows your priorities. Your code review agent knows your architecture. Every automated task runs with full context, never from scratch.

Commands

Upload Options

Already been using OpenClaw? All your conversation history and workspace knowledge is sitting on disk. openclaw mr upload discovers and uploads everything:

What gets uploaded automatically:

• Workspace files: MEMORY.md, memory/**/*.md, AGENTS.md, TOOLS.md
• Session transcripts from ~/.openclaw/agents/main/sessions/

Custom paths:

openclaw mr upload [path]              # Specific file or directory
openclaw mr upload --workspace <dir>   # Custom workspace directory
openclaw mr upload --brain <dir>       # Custom state dir (sessions from another agent)

After the initial upload, workspace file sync is automatic (see How Your Memory Stays in Sync). New conversations are stored automatically on every response.

Smart Storage

Only direct user ↔ AI conversation is stored. The following are excluded automatically:

• Tool use iterations (function calls, tool results)
• Subagent work
• Internal processing
• System noise (heartbeats, compaction flushes, audit messages)

This keeps your memory vault clean and relevant — no noise from intermediate tool calls or system overhead.

Supported Providers

MemoryRouter works with all major providers through OpenClaw:

Unsupported providers fall back to direct access automatically — no errors, no interruption.

Configuration

After running openclaw mr <key>, the config is stored in your OpenClaw config:

{
  "plugins": {
    "entries": {
      "mr-memory": {
        "enabled": true,
        "config": {
          "key": "mk_xxx",
          "endpoint": "https://api.memoryrouter.ai"
        }
      }
    }
  }
}

Multi-Agent

Running multiple agents on one gateway? Each agent gets its own memory vault. See the Multi-Agent Setup guide.

Custom Endpoint

If you're running a self-hosted MemoryRouter instance, the endpoint is configurable in the plugin config.

Disable / Remove

# Disable (restores all OpenClaw defaults, keeps your memories in the vault)
openclaw mr off

# Delete all memories
openclaw mr delete

# Uninstall the plugin entirely
openclaw plugins uninstall mr-memory

openclaw mr off restores everything to stock — built-in memory, workspace indexing, all defaults.

After OpenClaw Updates

After running openclaw update, update the plugin:

openclaw plugins update mr-memory

Pricing

Get your free memory key at app.memoryrouter.ai.