// Long-term memory engine for OpenClaw agents using M-flow knowledge graphs. Stores conversations as structured episodic memories and retrieves via graph-routed search. Use when the agent needs to remember past conversations, recall user preferences, or maintain context across sessions. Requires Docker.
| name | mflow-memory |
| description | Long-term memory engine for OpenClaw agents using M-flow knowledge graphs. Stores conversations as structured episodic memories and retrieves via graph-routed search. Use when the agent needs to remember past conversations, recall user preferences, or maintain context across sessions. Requires Docker. |
| requiredBinaries | ["docker"] |
| requiredEnvVars | ["LLM_API_KEY"] |
| homepage | https://github.com/FlowElement-ai/m_flow |
| repository | https://github.com/FlowElement-ai/m_flow/tree/main/openclaw-skill/mflow-memory |
Gives your agent persistent long-term memory powered by M-flow's cognitive memory engine.
Run once:
bash ~/.openclaw/skills/mflow-memory/scripts/setup.sh
This starts the M-flow MCP server and registers it with OpenClaw.
Follow these rules for every conversation:
Before answering, silently call search with the user's question to check for relevant memories. If memories are found, use them as context.
At the end of a conversation that contained meaningful information (decisions, facts, preferences, plans — not greetings or small talk), call save_interaction with the conversation content.
When the user explicitly asks you to remember something ("remember that I'm allergic to peanuts", "note that the deadline is Friday"), call save_interaction immediately — do not wait until the end of the conversation.
When the user says "remember", "last time", "before", "previously", or references past events, always call search first.
Do not store trivial exchanges, repeated information, or content the user asks you to forget.
After setup, these tools are automatically available:
save_interaction — Store a conversation as memory (preferred for dialogue)search — Search memories by natural language queryquery — Ask a question and get an answer grounded in memoriesmemorize — Build knowledge graph from previously added dataingest — One-step store + memorize (for documents)list_data — List stored datasetsdelete — Remove specific memoriesmemorize_status — Check if memorization is still processingprune — Reset all memory# Check if M-flow is running
bash ~/.openclaw/skills/mflow-memory/scripts/status.sh
# Restart
docker restart mflow-memory
# View logs
docker logs mflow-memory --tail 20
# Complete removal
bash ~/.openclaw/skills/mflow-memory/scripts/teardown.sh