workflowstacks
mcp-server

ClawMem: AI Agent Memory

On-device memory for AI agents. For founders building AI-powered tools with Claude Code, Hermes, and OpenClaw.

From the repo · “On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.”

211 stars+1★ this week41 forksTypeScriptGuide quality 8/10 · reviewed Jul 5Updated 10/20/2026100% free · open source
What it does

ClawMem provides an on-device memory layer for AI agents built with Claude Code, Hermes, and OpenClaw, enabling efficient storage and retrieval of data

When to use it
  • •You're building an AI-powered tool that requires fast and efficient data storage and retrieval
  • •Your application needs to integrate with Claude Code, Hermes, or OpenClaw for AI functionality
  • •You want to leverage hybrid RAG search and hooks for advanced data management
Ready-to-paste prompt
node src/index.ts --config config.json --mcp-server localhost:8080
Heads up: Ensure you have the necessary dependencies and TypeScript version installed, as specified in the ClawMem README, to avoid compilation errors
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/clawmem && curl -fsSL https://workflowstacks.com/api/skills/clawmem/claude-skill -o ~/.claude/skills/clawmem/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How ClawMem: AI Agent Memory works
Codeflow
Free to inspect

ClawMem: AI Agent Memory is a very large TypeScript project (~75k lines across 134 code files, plus 210 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size
Very large codebase
~75k lines · 134 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Node.js
Needs API keys (.env)
TypeScript 99%Python 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    bin/clawmem
    Where the program starts running
  4. 4
    package.json
    Dependencies and the commands it exposes
  5. 5
    .env.example
    The API keys and settings you must provide
What's in each folder
src/Core code — the actual logic120 files
agents/Prompts, skills & agent definitions1 files
bin/Command-line entry points1 files
docs/Documentation30 files
scripts/Helper scripts14 files
extras/Folder7 files
eval-bundles/Folder4 files
tests/Tests — proof it works210 files
READMEHas testsDocumentedNo CIMIT licenseUpdated this month
Quick Actions
Details
Creator
yoloshii
Language
TypeScript
Category
mcp-server
Published
2/6/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/clawmem.svg)](https://workflowstacks.com/skills/clawmem?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

MCP config

GitHub MCP config

Search repos, read code, open issues and PRs from Claude.

MCP config

Brave Search MCP config

Give Claude live web search via the Brave Search API.

MCP config

Puppeteer (browser) MCP config

Let Claude control a headless browser — navigate, screenshot, scrape.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 365,609
Rea: Reverse Engineer Apps
Inspect apps down to binary level with Rea. For founders needing code clarity.
mcp-server★ 156,480
open-webui: Self‑hosted AI Chat UI for Faster LLM Integration
Launch a sleek, web‑based AI interface that works with Ollama, OpenAI API, and more—ideal for founders needing a quick, customizable LLM front‑end. 153k+ GitHub stars.
mcp-server★ 132,268
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
mcp-server★ 89,194
worldmonitor: Real‑time Global Insight Dashboard for Founders
Gain instant situational awareness with AI‑curated news, geopolitics, and infrastructure data—all in one TypeScript dashboard. Ideal for founders needing fast, reliable OSINT.
mcp-server★ 452
dsh-memory
白箱AGI架构探索：元认知（自我认知循环）、持续学习（知识飞轮）、世界模型（条件空间+语义时空图）、自我改进（自举纪律）、零LLM白箱管线与可审计信任护栏。
mcp-server★ 3,294
neo: Self‑evolving AI team engine for live apps
Deploy an AI‑powered, self‑healing multi‑agent system that integrates Neural Link, GraphRAG and DreamService, letting founders automate complex app intelligence. 3.3k+ GitHub stars.