Claw Memory Bridge
Provides a shared memory bridge for AI agents (QClaw, Claude Code, Codex) allowing them to store, search, and retrieve notes, decisions, and conclusions via MCP tools, using local SQLite with optional TencentDB integration.
README
Claw Memory Bridge
Cross-agent shared memory bridge for MCP. Connects memory across QClaw, Claude Code, and Codex via MCP tools.
跨 Agent 共享记忆桥 — 通过 MCP 工具打通 QClaw、Claude Code、Codex 的记忆,让多个 AI agent 共享笔记与结论。
Features
- 存储与检索跨 agent 的笔记、决策、结论
- 按 agent 归档(
claude-code/codex/qclaw/user) - 全文搜索(SQLite FTS5,支持中文)
- 可选 TencentDB 集成(当存在
~/.openclaw/state/memory-tdai/时自动读取)
MCP Tools
| Tool | Description |
|---|---|
memory_store |
存一条记忆(agent + topic + content) |
memory_search |
全文搜索记忆(含 TencentDB 记忆库) |
memory_recent |
查看最近记忆 |
memory_context |
获取完整上下文:近期 + 相关 + TencentDB |
memory_status |
查看各 Agent 记忆量统计 |
Install
git clone https://github.com/ncepuee/claw-memory-bridge.git
cd claw-memory-bridge
npm install
Requires Node.js >= 22 (uses built-in node:sqlite).
Configure
Claude Code (stdio)
claude mcp add claw-memory-bridge --scope user -- node /path/to/claw-memory-bridge/server.js
Claude Code Plugin (Marketplace, recommended)
claude plugin marketplace add https://github.com/ncepuee/claw-memory-bridge
claude plugin install claw-memory-bridge@claw-memory-bridge
Plugin install auto-runs npm install for dependencies. Don't enable both stdio and plugin at the same time (same MCP name).
Codex
codex mcp add claw-memory-bridge -- node /path/to/claw-memory-bridge/server.js
Claude Desktop / other MCP clients
{
"mcpServers": {
"claw-memory-bridge": {
"command": "node",
"args": ["/path/to/claw-memory-bridge/server.js"]
}
}
}
Data
- Local SQLite:
~/.claw-memory-bridge/shared.db - Optional TencentDB:
~/.openclaw/state/memory-tdai/(auto-detected; skipped if absent)
Usage
Agents call memory_context at the start of a task to pull recent + relevant context, and memory_store at the end to persist key conclusions.
memory_store({
agent: "claude-code", // codex / qclaw / user
topic: "decision", // project / decision / conclusion / note
content: "我们在 XXX 项目上决定用 YYY 方案,因为 ZZZ",
source: "/path/to/file",
tags: "project=XXX,framework=YYY"
})
License
MIT © ncepuee
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.