skynetcmd

skynetcmd/m3-memory

Command

List registered agents and their last heartbeat. Useful for multi-agent setups.

skynetcmd/m3-memory

Command

GDPR Article 20 — export all memories you own as portable JSON.

skynetcmd/m3-memory

Command

Search captured chat-log turns from your prior Claude / Gemini sessions.

skynetcmd/m3-memory

Command

Delete a memory permanently. Asks for confirmation first.

skynetcmd/m3-memory

Command

Fetch one memory by UUID or short prefix.

skynetcmd/m3-memory

Command

Show memories related to a given one — knowledge-graph traversal up to 3 hops.

skynetcmd/m3-memory

Command

Health check — package version, installed payload, chatlog DB row count, per-agent hook state.

skynetcmd/m3-memory

Command

List all m3-memory slash commands and what they do.

skynetcmd/m3-memory

Command

Install or upgrade the m3-memory CLI + system payload.

skynetcmd/m3-memory

Command

Poll the inbox for new notifications addressed to you.

skynetcmd/m3-memory

Command

Auto-classified save — picks type/scope automatically, confirms before writing.

skynetcmd/m3-memory

Command

Hybrid memory search — FTS5 + semantic vector + MMR diversity rerank.

skynetcmd/m3-memory

Command

Chatlog subsystem status — row counts, queue depth, spill, last capture, hook health.

skynetcmd/m3-memory

Command

List your tasks and their state. Pass an argument to filter by state.

skynetcmd/m3-memory

Command

Direct memorywrite — explicit, no auto-classification. Use /m3:save for context-aware writes.

skynetcmd/m3-memory

Hook

Runs when a session starts, running an inline shell check. From skynetcmd/m3-memory.

skynetcmd/m3-memory

Hook

Runs before the context is compacted for auto tool calls, running an inline shell check. From skynetcmd/m3-memory.

skynetcmd/m3-memory

Hook

Runs when the agent finishes a response, running an inline shell check. From skynetcmd/m3-memory.

skynetcmd/m3-memory

MCP server Claude CodeCodexCursor +2

Give your AI agent a memory — local-first, private, easy to install. Guided setup wizard; works out of the box on your own machine, no cloud. For everyday agent users, homelabs, and developers alike · 99.2% LongMemEval-S retrieval @ k=10 · Works with Claude · Gemini · Antigravity · OpenCode · OpenClaw · Hermes · any…