ClawMem MCP server

On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.

What ClawMem does

Summarised from the project README; check the repository for the latest details.

Features

• Surfaces relevant context on every prompt (context-surfacing hook)
• Bootstraps sessions with your profile, latest handoff, recent decisions, and stale notes
• Captures decisions, preferences, milestones, and problems from session transcripts using a local GGUF observer model
• Generates handoffs at session end so the next session can pick up where you left off
• Learns what matters via a feedback loop that boosts referenced notes and decays unused ones
• Guards against prompt injection in surfaced content

Tools exposed (20+)

• __IMPORTANT – Workflow guide: prefer `memoryretrieve` → match query type to tool → `multiget` for full content
• memory_retrieve – Preferred entry point. Auto-classifies query and routes to optimal backend (query, intentsearch, sessionlog, findsimilar, or queryplan). Use
• search – BM25 keyword search — for exact terms, config names, error codes, filenames. v0.24.0: non-recency queries rank by the RAW BM25 transform (`s
• vsearch – Vector semantic search — for conceptual/fuzzy matching when exact keywords are unknown. v0.22.0: non-recency queries rank by RAW cosine (`sc
• query – Full hybrid pipeline (BM25 + vector + rerank) — general-purpose when query type is unclear. WRONG for "why" questions (use `intentsearch`) o
• get – Retrieve single document by path or docid
• multi_get – Retrieve multiple docs by glob or comma-separated list
• find_similar – USE THIS for "what else relates to X", "show me similar docs". Finds k-NN vector neighbors — discovers connections beyond keyword overlap th
• intent_search – USE THIS for "why did we decide X", "what caused Y", "who worked on Z". Classifies intent (WHY/WHEN/ENTITY/WHAT), traverses causal + semanti
• query_plan – USE THIS for complex multi-topic queries ("tell me about X and also Y", "compare A with B"). Decomposes into parallel typed clauses (bm25/ve
• build_graphs – Build temporal and/or semantic graphs from document corpus
• find_causal_links – Trace decision chains: "what led to X", "how we got from A to B". Follow up `intentsearch` with this tool on a top result to walk the full c
• kg_query – Query the SPO knowledge graph: "what does X relate to?", "what was true about X when?". Returns temporal entity-relationship triples with va
• memory_evolution_status – Show how a document's A-MEM metadata evolved over time
• timeline – Show the temporal neighborhood around a document — what was created/modified before and after it. Progressive disclosure: search → timeline
• beads_sync – Sync Beads issues from Dolt backend (`bd` CLI) into memory: syncs the full backlog (no 50-issue cap), creates docs, bridges all dep types to
• list_vaults – Show configured vault names and paths. Empty in single-vault mode.
• vault_sync – Index markdown from a directory into a named vault. Restricted-path validation rejects sensitive directories.
• diary_write – Write a diary entry. Use for recording important events, decisions, or observations in environments without hook support. Stored as searchab
• diary_read – Read recent diary entries. Filter by agent name.

Requirements

• Bun v1.0+ — runtime for ClawMem. On Linux, install via `curl -fsSL https://bun.sh/install | bash` (not snap — snap Bun cannot read stdin, which breaks hooks).
• SQLite with FTS5 — included with Bun. On macOS, install `brew install sqlite` for extension loading support (ClawMem detects and uses Homebrew SQLite automatically).
• llama.cpp (`llama-server`) — for dedicated GPU inference. Without it, `node-llama-cpp` runs models in-process (auto-downloads on first use). GPU servers give better throughput and prevent silent CPU fallback.
• systemd (Linux) or launchd (macOS) — for persistent background services (watcher, embed timer, GPU servers). ClawMem ships systemd unit templates; macOS users can create equivalent launchd plists. See systemd services.
• Claude Code — for hooks + MCP integration

How to install ClawMem

Listed on Socketlist – add this badge to your README:

Badge markdown[](https://socketlist.pages.dev/s/yoloshii-clawmem/)

Maintain this project? Get it featured for free during launch →

Compare with codebase-memory-mcp →

Related Databases MCP servers