Maximem Memory Plugin for OpenClaw / MoltBot

``bash
npm install @maximem/memory-plugin
`

OpenClaw plugin and MoltBot plugin for persistent cross-channel memory. Uses the Maximem backend for auto recall and auto capture: before_agent_start the plugin recalls relevant memories; at agent_end it captures conversation context.

Features

- Auto-Recall: Automatically injects relevant memories before each LLM turn
- Auto-Capture: Automatically stores conversation context after each turn
- Slash Commands: /remember and /recall for direct memory interaction
- OpenClaw Agent: maximem_store, maximem_search, maximem_forget for agent-driven memory operations
- CLI Commands: Terminal-based memory management with openclaw maximem
- Cross-Channel: Memories persist across Telegram, Slack, WhatsApp, Discord, and all supported channels

How it works

- before_agent_start → recall (inject relevant memories into context)
- agent_end → capture (store conversation context)

API Key

Get your API key from Maximem AI.




Installation

$3

`bash
openclaw plugins install @maximem/memory-plugin
`

$3

`bash
openclaw plugins list
openclaw plugins info memory-plugin
openclaw plugins doctor
`

Configuration

Option 1: Environment Variable (Recommended)

$3


`
echo 'export MAXIMEM_API_KEY="mx_..."' >> ~/.zshrc
source ~/.zshrc
`

$3

`
echo 'export MAXIMEM_API_KEY="mx_..."' >> ~/.bashrc
source ~/.bashrc
`

$3

`
[System.Environment]::SetEnvironmentVariable("MAXIMEM_API_KEY", "mx_...", "User")
`

Option 2: Config File

Edit ~/.openclaw/openclaw.json:

`json
{
"plugins": {
"entries": {
"memory-plugin": {
"enabled": true,
"config": {
"apiKey": "mx_...",
"autoRecall": true,
"autoCapture": true,
"maxRecallTokens": 1000,
"minPromptLength": 5,
"captureDebounceMs": 2000
}
}
}
},
"agents": {
"list": [{
"id": "main",
"tools": {
"allow": ["maximem_store", "maximem_search", "maximem_forget"]
}
}]
}
}
`

$3

| Option | Type | Default | Description |
|--------|------|---------|-------------|
| apiKey | string | - | Maximem API key (or set MAXIMEM_API_KEY env var) |
| autoRecall | boolean | true | Automatically inject memories before each turn |
| autoCapture | boolean | true | Automatically capture conversation after each turn |
| maxRecallTokens | number | 1000 | Maximum tokens for recalled memory context (100-10000) |
| minPromptLength | number | 5 | Minimum prompt length to trigger recall |
| captureDebounceMs | number | 2000 | Debounce window for batching captures (milliseconds) |

Usage

$3

Use these commands directly in any supported chat channel (Whatsapp, Slack, etc.):

#### /remember [text]

Manually save information to long-term memory:

`
/remember My favorite programming language is TypeScript
/remember I prefer dark themes for all applications
/remember Project deadline is March 15, 2026
`

#### /recall [query]

Search your long-term memory:

`
/recall favorite programming language
/recall project deadline
/recall preferences
`

$3

Manage memories from the terminal:

#### Search Memories

`bash
openclaw maximem search "favorite color"
openclaw maximem search "deadlines" --limit 20
openclaw maximem search "preferences" --category preference --json
`

$3

Enable tools in your agent configuration to let the Agent use memory operations:

`json
{
"agents": {
"list": [{
"id": "main",
"tools": {
"allow": ["maximem_store", "maximem_search", "maximem_forget"]
}
}]
}
}
``

The Agent can then autonomously:
- Store important facts when users share information
- Search memories when answering questions about past conversations
- Forget specific memories when requested

Support

- Documentation: memoryplugin-for-openclaw.com

- Issues: GitHub Issues
- Email: shreyansh.g@maximem.ai