BrainHub

BrainHub

A unified FastAPI web panel and single MCP gateway that aggregates knowledge base, cloud drive, kanban, memory, and ops agent capabilities for the Brain product family.

Category
Visit Server

README

BrainHub — 统一 Web 前端 + 网盘 + MCP 网关 + 运维 agent

Brain 产品族的自用主入口：一个 FastAPI 单进程聚合所有面板（知识库 / 搜索 / 网盘 / 看板 / 记忆 / agent 状态 / 运维日志），对外提供单一 MCP 网关，内置运维 agent 自动维护知识库与记忆。

简介

BrainHub 是 Brain 产品族的使用入口，负责把产品族全部能力收拢到一个可操作的界面与一套 API 里：

  • Web 面板：Jinja2 + HTMX 零前端构建，知识库浏览 / 语义搜索 / 网盘 CRUD / 看板任务状态机 / 记忆 / agent 状态 / 运维日志
  • JSON API v1：/api/v1/* 供桌面端 React 前端调用
  • MCP 网关：聚合 BrainHub 自有工具 + BrainMem 检索工具共 12 个，任何 agent 只连这一个入口
  • 运维 agent：定时归档、索引重建、记忆提取、健康检查

自用期一个 brainhub start 把主进程全部拉起：import brainmem 当检索后端、拉起 brain-bridge 子进程，对外像一个软件。

特性

  • 🖥️ 统一面板 — 7 类页面聚合在一个服务，HTMX 局部刷新 + Alpine 轻交互，无需前端构建链
  • 🔌 单一 MCP 入口 — write_note / read_file / list_files / 项目状态机 / health_check / send_matrix_msg + 转发 BrainMem 检索工具
  • 🤖 运维 agent — APScheduler 定时：归档 / 索引重建 / 记忆提取 / 健康检查，无需外部编排
  • 📁 网盘 — BRAIN_ROOT 文件浏览、上传下载、缩略图懒生成、越界与敏感路径拦截
  • 📋 看板 — 项目/任务状态机（todo → doing → blocked → done，严格流转）
  • 🔗 协作对接 — 经命名管道把 send_matrix_msg 转发给 BrainBridge daemon，前端 WS 实时收 Matrix 消息与 agent 状态
  • 💻 桌面端同源挂载 — /app 挂载 brainhub-desktop 构建产物，同源免 CORS

架构组成

目录 职责
web/ FastAPI 应用 + Jinja2 模板 + WS；routes/api.py 为桌面端 JSON API v1
storage/ 文件 CRUD + 缩略图、write_note 归档、共享 memory.db 的懒加载 Store
projects/ 项目/任务状态机模型
ops/ 运维 agent：记忆提取、OpsAgent 接口、APScheduler 定时
pipe/ 命名管道客户端（与 BrainBridge 通信，envelope 对齐协议宪法 §3）
mcp.py fastmcp 网关：自有工具 + 转发 BrainMem 工具
cli.py brainhub start / stop / status + ops 子命令

快速开始

# 安装（Python 3.10+，uv 管理；依赖 BrainMem editable 安装）
uv sync
uv pip install -e ../brainmem

# 启动（拉起 Web + MCP 网关 + brain-bridge 子进程）
uv run brainhub start

# 运维子命令
uv run brainhub ops archive
uv run brainhub ops reindex
uv run brainhub ops health

文档索引

相关项目

Brain 产品族：BrainMem（记忆引擎）· BrainHub（本仓库）· BrainBridge（协作网关）

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured