RN

raphasouthall/neurostack

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

47 stars 5 forks 质量 72 趋势 27Apache-2.0

本地RAG层和优化器,用于你的Markdown知识库。CLI + MCP服务器:为任何AI客户端提供有据的解决方案,支持陈旧笔记检测,会话采集到内存。本地优先。

概览

NeuroStack 将一个包含 .md 文件(Obsidian、Logseq、Notion exports、纯 Markdown)的文件夹索引到 SQLite,使用 FTS5、嵌入和维基链接图,并作为搜索、图查询和代理记忆向任何 MCP 客户端开放。检索返回排名证据,AI 负责推理——在等待查询时不会运行模型。NeuroStack 则保持基础准确:标记已陈旧的笔记,将 AI 会话中的决策和根本原因收集到记忆中,将重复记忆合成学习内容,并将经过验证的记忆排队以提升到笔记中。索引永远不会修改你的文件。可选的 MCP 写入工具允许客户端通过你的 git 历史编写或编辑笔记。 可兼容 Claude、Cursor、Windsurf、Gemini CLI、VS Code、Codex 及任何支持 MCP 的其他客户端。

概述(AI 翻译)

本地检索层和你已有Markdown知识库的优化器。

NeuroStack 将包含 .md 文件(Obsidian、Logseq、Notion exports、plain Markdown)的文件夹索引到一个 SQLite 数据库,支持全文搜索、嵌入和维基链接图。任何 MCP 客户端都可以搜索、游走图表并保存记忆。查询返回带有笔记路径的排序证据,AI 负责推理,因此等待时模型不会运行。查询间隙,NeuroStack 保持知识库准确。它标记已陈旧的笔记,收集 AI 会话中的决策和根本原因,将重复记忆合并为学习内容,并将已验证的记忆排队成笔记。索引永远不会改变文件,可选的 MCP 写入工具允许客户端通过你的 git 历史编辑笔记。

可兼容 Claude、Cursor、Windsurf、Gemini CLI、VS Code、Codex 及任何支持 MCP 的其他客户端。

60秒开始

以下步骤将解释每个部分以及如何连接其他AI客户端。


你的笔记,在你掌控之中

默认情况下,NeuroStack 是一个只读索引层:

  • 索引、搜索、摘要和图表分析 切勿修改您的Markdown文件

本页由 AI 翻译,技术细节请以原文为准。

README

以下为原文 README 节选,完整内容请查看原文。

A local retrieval layer and optimizer for the Markdown knowledge base you already have.

NeuroStack indexes a folder of .md files (Obsidian, Logseq, Notion exports, plain Markdown) into one SQLite database with full-text search, embeddings and a wiki-link graph. Any MCP client can then search it, walk the graph and save memories. A query returns ranked evidence with note paths, and your AI does the reasoning, so no model runs while you wait. Between queries NeuroStack keeps the knowledge base accurate. It flags notes that have gone stale, harvests decisions and root causes from your AI sessions, merges recurring memories into learnings, and queues the proven ones to become notes. Indexing never changes your files, and optional MCP write tools let a client edit notes through your git history.

Works with Claude, Cursor, Windsurf, Gemini CLI, VS Code, Codex and any other client that supports MCP.

60-second start

npm install -g neurostack          # install
neurostack init                    # pick your notes folder, press Enter for the rest
/save                              # in omp or Claude Code, keep what this session learned
neurostack doctor                  # check that everything works

The steps below explain each part and how to connect other AI clients.


Your notes, in your control

By default, NeuroStack is a read-only indexing layer:

  • Indexing, search, summaries, and graph analysis never modify your Markdown files
  • All index data lives in NeuroStack’s own separate database
  • To remove it completely, run neurostack uninstall. Your notes stay untouched.
  • Nothing ever leaves your machine, unless you configure a third-party LLM provider for summaries and embeddings

If your vault is a git repo, four opt-in MCP write tools let an AI client author and edit notes for you: vault_write_file, vault_delete_file, plus vault_read_file / vault_list_files. Every write commits and pushes to your git remote with a descriptive message, so every change is visible in git log, revertable with git revert, and serialised under a per-vault lock. Writes hard-reject invalid frontmatter, paths outside the vault, and hidden directories (.git, .obsidian, …). Because the tools are exposed to any client talking to neurostack serve, gate them at the transport (auth, tunnel, LAN only) if you put the MCP endpoint on the public internet.


在 GitHub 查看完整 README

安装

This server does not publish a one-line install command.

Open the repository installation guide 新手?先看 mcpskill.org 教程 →