linggen
Local, privacy-focused RAG service for code search via MCP. https://linggen.dev
可用工具 （5 个）
该服务在 MCP 协议中暴露的工具，AI 可按需调用
tavily_search 14 个参数 需填 1 项
Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.
必填参数：query
tavily_extract 6 个参数 需填 1 项
Extract content from URLs. Returns raw page content in markdown or text format.
必填参数：urls
tavily_crawl 11 个参数 需填 1 项
Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.
必填参数：url
tavily_map 8 个参数 需填 1 项
Map a website's structure. Returns a list of URLs found starting from the base URL.
必填参数：url
tavily_research 2 个参数 需填 1 项
Perform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources to answer a question or complete a task. Returns a detailed response based on the research findings.
必填参数：input
服务介绍
# Linggen
Linggen is a local-first RAG + MCP memory layer for AI coding assistants.
It runs entirely on your machine, is free for individuals and teams, and is built for:
-
Working across many projects with one shared memory layer
-
Navigating huge codebases and documentation sets
-
Connecting multiple IDEs/agents via MCP (Cursor, Zed, Windsurf, etc.)
Nothing leaves your machine by default: embeddings, indexes, and search all run locally.
# What You Can Do
-
Index your world: local folders, codebases, docs, and notes
-
Semantic search + AI chat over everything you've indexed
-
Expose an MCP server at
http://localhost:8787/mcp/ssefor compatible tools -
Run it for a team on a shared machine and point everyone's MCP config at it
See the full product docs at linggen.dev.
# Install (App)
-
Download the latest macOS build from GitHub Releases:
https://github.com/linggen/linggen-releases/releases -
Open the
.dmgand drag Linggen intoApplications. -
On first launch, it downloads an embedding model (~100MB) and starts a local backend at
http://localhost:8787.
Currently macOS only. Windows & Linux are planned.
# MCP Setup (Cursor)
Linggen starts an MCP server at http://localhost:8787/mcp/sse.
Add this to ~/.cursor/mcp.json to connect Cursor:
{
"mcpServers": {
"linggen": {
"url": "http://localhost:8787/mcp/sse"
}
}
}
Restart Cursor and you should see linggen as a connected MCP server.
# This Repo
This repo is the Linggen landing page and docs site, built with React and Vite, deployed to Cloudflare Pages.
npm install
npm run dev
