I run IT and cybersecurity ops by day and tinker in a homelab at night. The problem I kept hitting: useful context from Cursor and Claude Code sessions evaporates when the chat ends. Notes end up scattered. RAG demos are cloud-first. I wanted something I own.
So I built Brain AI Hub  a portable second brain with a local LLM, markdown vault, semantic search, and MCP hooks for IDE agents.
:11434
.brain-vault
, brain-library
, brain-rag
) with one-click deploy to Cursor, Claude Code, VS Code.:7860
for services, chat, GPU/VRAM, API keys, pipeline status.| Edition | Install |
|---|---|
Windows portable |
Install.bat → Start.bat  copy the folder, run on another PC |
Linux server |
`curl -fsSL …/linux/bootstrap.sh \ |
Install scripts speak English and Polish ({% raw %}locale.env
: LANG=en
or LANG=pl
).
On Windows, Brain deploys stdio MCP configs from the dashboard. On Linux, point Cursor at the SSE gateway:
{
"mcpServers": {
"brain-rag": {
"url": "http://192.168.1.10:7862/sse/brain-rag"
}
}
}
Agents can search your vault, pull library chunks, and run skills without sending data to a third-party memory API.
RAG answers retrieval. MCP gives agents tools  write a note, list vault files, trigger a skill, query the code index. That matches how Cursor and Claude Code actually work: function calls mid-session, not a single embedding search at prompt time.
Python, FastAPI, Ollama, sqlite-vec, PowerShell (Windows), systemd (Linux). Homelab-friendly: MikroTik/UniFi networking, WireGuard, Docker where it helps.
git clone https://github.com/lobrzut/brain.git
cd brain
Open http://127.0.0.1:7860
, connect MCP from the Tools tab, drop a PDF in the library, run a distill job on an old chat export.
Related homelab projects: AI Studio (ComfyUI + ACE-Step) and NetDash (LAN service dashboard).
Feedback and issues welcome on GitHub.