ClawMem

On-device memory layer over your markdown notes: hooks plus a 33-tool MCP server, no API keys.

AdaptableOperable MCP serverMCP server Hybrid TypeScript MCP server License: MIT

ClawMem indexes a folder of markdown notes and project docs into a local SQLite vault with hybrid retrieval (BM25 plus local embeddings and reranking), then surfaces context into Claude Code, OpenClaw, or Hermes on every prompt through lifecycle hooks. An MCP server exposes search, timeline, and causal-link tools for targeted retrieval. Fully local; MIT.

Use it when

you want Claude Code to remember your project decisions without sending notes to a cloud
you run OpenClaw or Hermes agents and want them sharing one memory with your coding sessions

Gotchas

Needs Bun; native Windows is not recommended, use WSL2
SOTA embedding stack wants 16GB+ VRAM; smaller hardware falls back to CPU models or a cloud embedding endpoint
Snap-installed Bun cannot read stdin, which breaks hooks (README)
Sits at the agent-memory edge of notes-knowledge; flagged for the Curator

Last activity Aug 18, 2026. Fit: adaptable 3, operable 3.

Editions

Free · Free open source

Clonegit clone https://github.com/yoloshii/ClawMem
Installnpm install -g clawmem && clawmem bootstrap ~/notes --name notes

For agents: JSON · Markdown

Adaptable: what is yours to change

Make it yours

Config only15 things to edit

clawmem bootstrap ~/notes does init, index, embed, hooks, and MCP registration in one go. The business surface is ~/.config/clawmem/config.yaml: named collections with a glob pattern each (default **/*.md) and optional named vaults (or CLAWMEM_VAULTS), which decide what the agent remembers; SKILL.md holds the retrieval rules the agent follows. .env.example names only model plumbing: CLAWMEM_EMBED_URL, CLAWMEM_EMBED_MODEL, CLAWMEM_EMBED_DIMENSIONS, CLAWMEM_EMBED_API_KEY, CLAWMEM_RERANK_URL, CLAWMEM_LLM_URL, CLAWMEM_NO_LOCAL_MODELS; CLAWMEM_HEAVY_LANE and CLAWMEM_JUDGE_* switch optional lanes. Hooks land in Claude Code settings.json.

Env vars: CLAWMEM_EMBED_URL CLAWMEM_EMBED_MODEL CLAWMEM_EMBED_DIMENSIONS CLAWMEM_EMBED_API_KEY CLAWMEM_EMBED_TPM_LIMIT CLAWMEM_RERANK_URL CLAWMEM_LLM_URL CLAWMEM_NO_LOCAL_MODELS CLAWMEM_API_TOKEN CLAWMEM_HEAVY_LANE CLAWMEM_VAULTS
Config files: ~/.config/clawmem/config.yaml .env ~/.claude/settings.json
Prompt files: SKILL.md
Accounts you need: none

Source

github.com/yoloshii/ClawMem
MIT license
Last commit Aug 18, 2026
207 stars

Operable: what an agent can drive

Interface

NativeMCP serverpublished by the builderlocal

How an agent can drive an Operable Listing, in five levels: native (built for the agent as the primary interface), official (the Builder ships an agent interface), wrapped (a third party wraps the software's API), config (an agent can only drive it by editing files), gui (screen control only). An interface is official only when it is published by the same organization that ships the software. GUI-level Listings are allowed and sorted last.

Docs: github.com/yoloshii/ClawMem#readme
Tools: memory_retrieve search vsearch query query_plan intent_search timeline find_causal_links

Reach

Partial coverage. 6 of 9 jobs reachable through the stated interface.

Job	Through the interface	Evidence
Retrieve relevant notes for a prompt	Reachable	memory_retrieve, query, search, vsearch, intent_search MCP tools; context-surfacing hook does it automatically
Navigate the timeline around a document	Reachable	timeline tool
Find causal links between decisions	Reachable	find_causal_links tool
Capture decisions and session handoffs	Reachable	Stop and PreCompact hooks run decision extraction and precompact-extract
Detect and decay contradicted decisions	Reachable	runs when a judge is configured with CLAWMEM_JUDGE_*; disabled otherwise
Index additional collections	Not reachable	clawmem collection add is CLI; pattern per collection in config.yaml
Import chat exports (Claude, ChatGPT, Slack)	Not reachable	clawmem mine is a CLI command, not an MCP tool
Sync Beads issues into memory	Not reachable	CLI plus bd; not an MCP tool
Query across multiple vaults	Reachable	retrieval tools accept an optional vault parameter

Code stack

Languages: TypeScript
Frameworks: Bun
Package manager: bun
Database: SQLite (FTS5, sqlite-vec)
Hosting target: local
Built: Unknown (recorded, never ranked)

Model stack

Providers: local embedding and reranker models (zembed-1, zerank-2, QMD combo)optional OpenAI-compatible embedding endpoint
Models: zembed-1zerank-2
Keys you need: CLAWMEM_EMBED_API_KEY CLAWMEM_EMBED_URL CLAWMEM_LLM_URL CLAWMEM_RERANK_URL
Prompts live in: SKILL.md

Skills

A root SKILL.md teaching an agent to use the ClawMem memory MCP server.

Kind: bundled
Paths: SKILL.md

Evidence and confidence

Field	Where it was seen	Confidence
formFactor	README: MCP stdio server plus hooks and CLI; registered in ~/.claude.json	90%
executionModel	runs local embedding and reranker models; optional LLM synthesis and judge	75%
operability	hooks and MCP are the product; README 'On-device memory for Claude Code, OpenClaw, and Hermes'	90%
effort	.env.example CLAWMEM_* names; README names ~/.config/clawmem/config.yaml	80%
editions	MIT, npm package, no paid edition	95%
active	pushedAt 2026-08-18; Show HN 2026-03-22	–
provenance	CLAUDE.md, AGENTS.md, SKILL.md present; no authorship statement	30%
reach		80%

Open questions

Full list of the 33 MCP tools
Which CLAWMEM_JUDGE_* names exist and what provider they expect

Sources

github.com/yoloshii/ClawMem sourcing:notes-knowledge:community