brain.md

A local-first second brain for you — and for your AI agents.

What you get

Why brain.md

LLMs are only as smart as the context you give them. brain.md turns your notes into that context — without dragging them into someone else's cloud, without locking them inside a proprietary format, and without asking you to plumb a vector database yourself.

You write markdown. brain.md gives you:

• a polished editor + live preview with the full Obsidian-flavor dialect (wikilinks, embeds, callouts, math, mermaid, highlights, tasks, frontmatter, aliases),

• a per-vault LanceDB vector store with a local bge-small-en-v1.5 embedder by default — switch to Ollama, LM Studio, OpenAI, or anything else with a /v1/embeddings endpoint with one toggle,

• an MCP server (streamable HTTP) mounted on the same port, so Claude Desktop (or any MCP client) can read, search and write your notes safely — with per-folder read/write permissions for the agent surface,

• optional password auth and git autocommit / restore for the whole vault.

Everything runs on your machine. The vault is a plain folder of .md files you can open in any editor at any time.

How it compares

brain.md is not trying to replace Obsidian's plugin ecosystem or Notion's databases. It's narrower on purpose: a markdown vault designed from day one as a memory layer for AI agents over the Model Context Protocol.

Table of contents

• Quick start

• Install

• The interface

  • Editor + preview

  • Markdown that actually does things

  • Command palette + quick switcher

  • Tasks across the vault

• AI for agents

  • Semantic search (RAG)

  • MCP server

  • Per-folder permissions

  • Optional password auth

• CLI

• Defaults & paths

• Architecture

• Roadmap

• Contributing

• License

⚡ Quick start

One line. No clone, no Bun, no Node — the installer detects your OS + arch, downloads the matching prebuilt binary from the latest GitHub release, drops it in ~/.local/bin (or %USERPROFILE%\.brain.md\bin on Windows), and verifies it runs.

macOS / Linux

curl -fsSL https://raw.githubusercontent.com/mi4uu/brain.md/main/install.sh | bash

Windows (PowerShell)

powershell -c "irm https://raw.githubusercontent.com/mi4uu/brain.md/main/install.ps1 | iex"

Then:

brainmd                  # serve on :3000, vault at $HOME/.local/share/brain.md/vault
open http://localhost:3000

Open http://localhost:3000. First run creates your vault at the XDG default ($HOME/.local/share/brain.md/vault on macOS / Linux, the equivalent on Windows).

To enable semantic search and the MCP similar_notes tool, open Settings → AI / RAG and flip the switch. Default embedder is bge-small-en-v1.5 running locally via Xenova ONNX (one-time ~133 MB model download, then fully offline).

Want a tour? Point brain.md at the demo vault that ships with the repo:

brainmd --vault-dir ./example/vault

Every screenshot below was taken against example/vault/.

📦 Install

Option A — install script (recommended, see Quick start)

# macOS / Linux
curl -fsSL https://raw.githubusercontent.com/mi4uu/brain.md/main/install.sh | bash

# Windows
powershell -c "irm https://raw.githubusercontent.com/mi4uu/brain.md/main/install.ps1 | iex"

The script picks the right asset for your OS and CPU, writes it to ~/.local/bin/brain (or %USERPROFILE%\.brain.md\bin\brain.exe), chmod's it, and verifies it boots. Pin a version with BRAIN_VERSION=v0.1.0, change the install dir with BRAIN_INSTALL=….

Option B — download the binary manually

Every release ships a single-file executable per platform with the web UI embedded inside it. No Bun runtime, no Node.js, no git clone, no bun install — just download, mark executable, run.

Grab the file for your machine from the latest release: 👉 github.com/mi4uu/brain.md/releases/latest

One-liner — macOS / Linux

# macOS Apple Silicon — swap the URL suffix for your platform from the table above
curl -L -o brainmd \
  https://github.com/mi4uu/brain.md/releases/latest/download/brain-md-darwin-arm64
chmod +x brainmd
./brainmd                                # → serves on http://localhost:3000

# Optional: drop it on your $PATH so you can run `brainmd` anywhere
sudo mv brainmd /usr/local/bin/brainmd
brainmd --help                           # see all flags
brainmd --port 4000                      # custom port
brainmd --vault-dir ~/notes/my-vault     # custom vault location

One-liner — Windows (PowerShell)

iwr https://github.com/mi4uu/brain.md/releases/latest/download/brain-md-windows-x64.exe `
    -OutFile brainmd.exe
.\brainmd.exe                            # → serves on http://localhost:3000
.\brainmd.exe --help                     # all flags

First run: brain.md creates an empty vault at the XDG default ($HOME/.local/share/brain.md/vault on macOS/Linux, the equivalent on Windows) and serves the editor at http://localhost:3000. Want to try the demo vault first? Download example/vault/ and pass it with brain --vault-dir ./vault.

Untagged commits also produce binaries — they live as build artifacts on the Actions page with 30-day retention.

Option C — from source

git clone https://github.com/mi4uu/brain.md.git
cd brain.md
bun install
bun run start            # runs the production server on :3000

For development:

bun run dev:server       # backend on :3000
bun run dev:web          # vite on :5173 (with /api proxy)

If you run bun run start from a fresh source checkout (no compiled binary, no web/dist), the server downloads the matching web bundle from the GitHub release into $XDG_CACHE_HOME/brain.md/web/<version>/ on first request and serves from there. To always work offline, run bun --cwd web run build once.

Requires Bun ≥ 1.3. brain.md uses Bun.password (built-in argon2id) so you don't need a native crypto build.

🖥️ The interface

Editor + preview

Two synchronised panes powered by CodeMirror 6 and a unified / remark / rehype rendering pipeline. The active block in the preview stays anchored to the cursor in the editor; a thin SVG connector marks the link between them.

The right rail collects Bookmarks · Vault · Tags · Outline · Backlinks · Related. Each section is collapsible and remembers its state per device (localStorage). The Tags panel splits into In this note and Other tags the moment you open a note. The Related panel powers itself from the RAG index — same engine the agents use — and after every save brain.md quietly suggests up to three tags borrowed from your closest semantic neighbours.

Markdown that actually does things

Callouts

Math (KaTeX)

Mermaid diagrams

Syntax-highlighted code

Command palette + quick switcher

• ⌘P / Ctrl+P — search across titles and bodies

• ⌘O / Ctrl+O — fuzzy quick switcher

Both are powered by cmdk inside a Radix Dialog.

Tasks across the vault

Every - [ ] and - [x] in your notes is collected into a single view, with filters for open / done / all and a click-through to the source line.

🤖 AI for agents

This is what makes brain.md more than another markdown editor.

🔍 Semantic search (RAG)

When a note is saved, brain.md chunks it (≤ 512 tokens, ~64-token overlap, paragraph-aligned, frontmatter excluded), embeds each chunk, and upserts the vectors into a per-vault LanceDB table at <VAULT>/.brain/lance/.

Running the prebuilt binary? The Xenova local embedder pulls in onnxruntime-node, which loads a platform-specific native library (libonnxruntime.so / .dll / .dylib) at runtime. bun --compile does not bundle that, so the embedder will throw libonnxruntime.so.X: cannot open shared object file on first use. The smoothest fix: run Ollama locally and switch the provider in Settings → AI / RAG to OpenAI-compatible, baseURL = http://localhost:11434/v1, model = nomic-embed-text (ollama pull nomic-embed-text first), dim = 768. Local Xenova works out of the box when you run from source (bun run dev).

REST surface:

Related notes, in the sidebar

The same engine the agents use also powers a Related panel in the sidebar. Open any note → the panel lists semantically close neighbours with score, line range and a snippet preview. Click jumps you there.

Tag suggestions on save

After every save, brain.md quietly looks at the closest neighbours' frontmatter tags and suggests up to three you haven't used yet. One click drops the tag into your frontmatter.

🛰️ MCP server

brain.md mounts a Model Context Protocol server on the same Elysia app at POST /mcp. Transport is the 2024-11-05 streamable HTTP variant in stateless JSON-response mode — one POST returns the full JSON-RPC response in a single round trip, no SSE stream, a fresh McpServer + transport per request. Sounds wasteful, but it's the only mode that survives clients that open and close a transport per tool call (Claude Desktop and LM Studio both do this).

Tools (16):

Resources (2):

• vault://tree — JSON {folders, notes} filtered by read perms

• vault://note/<path> — markdown body

Drop this into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or the equivalent on your OS:

{
  "mcpServers": {
    "brain.md": {
      "type": "streamable-http",
      "url": "http://localhost:3000/mcp"
    }
  }
}

That's it — restart Claude Desktop and you'll see the tools appear. Full reference: docs/mcp.md.

🔒 Per-folder permissions

Right-click any folder → MCP permissions… to set explicit {read, write} flags. Resolution walks the parent chain to root; nearest explicit override wins; default is read + write.

This is how you keep Journal/Private/ out of agent reach without locking down the whole vault.

🔑 Optional password auth

Default: no auth. Set a password in Settings → Security to switch on bearer-token authentication for both the HTTP API and the MCP endpoints. Password is hashed with argon2id (Bun's built-in Bun.password, no native crypto build needed); tokens live in memory with a 24-hour TTL.

MCP config when auth is enabled

The plain-text MCP example earlier in the README assumes no auth. When you turn auth on, every request to /mcp needs an Authorization: Bearer <token> header. Most MCP clients have a field for it:

Claude Desktop / Claude Code / Cursor (claude_desktop_config.json):

{
  "mcpServers": {
    "brain.md": {
      "type": "streamable-http",
      "url": "https://brainmd.example.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_TOKEN_HERE"
      }
    }
  }
}

How to get a token. brain.md issues tokens through POST /api/auth/login. You can do it from anywhere — most useful is a quick curl:

curl -X POST https://brainmd.example.com/api/auth/login \
  -H 'content-type: application/json' \
  -d '{"password":"YOUR_PASSWORD"}' | jq -r .token

Paste the returned token into the headers.Authorization field above, restart the MCP client, done.

Heads-up. Tokens have a 24-hour TTL and are stored in memory only — a server restart invalidates every token. If your agent suddenly starts seeing 401 Unauthorized, get a fresh token. Long-term: pin the token on the client and let your agent re-login on 401 (most MCP clients don't do this yet — patches welcome).

If you're embedding the URL itself anywhere persistent, prefer a secret-manager / .env over hard-coding the bearer string.

⌨️ CLI

brainmd [options]            # or: bun run start
brainmd --help               # -h
brainmd --version
brainmd --vault-dir <path>   # -v <path>
brainmd --port <n>           # -p <n>
brainmd --mcp-disabled       # skip mounting MCP at /mcp/*

Precedence: CLI flag > env var > XDG default. Unknown flag → stderr error + exit 2.

🗂️ Defaults & paths

Same logic on macOS, Linux, Windows — no OS branching. The vault dir is mkdir -p-ed on first run.

Per-vault state lives under <VAULT>/.brain/:

<VAULT>/
├── Welcome.md
├── Folder/
│   ├── Note.md
│   └── .media/
│       └── img.png
└── .brain/
    ├── index.json          # mtime-based search index
    ├── settings.json       # bookmarks, dailyDir, git autocommit, rag config
    ├── folder-meta.json    # icons, colors, per-folder MCP perms
    ├── auth.json           # argon2id hash — absent when auth is off
    ├── lance/              # LanceDB tables (RAG), git-ignored
    └── trash/<ts>/...      # recoverable deletes

Every env knob:

🏗️ Architecture

+----------------+        /api/*        +-------------------+
|  React + CM6   | <------------------> |                   |
|  web client    |                      |                   |
+----------------+                      |   Elysia (Bun)    |  +-------------+
                                        |                   |  | Vault FS    |
+----------------+   /mcp HTTP+SSE      |   - Vault         |  | .brain/     |
| Claude Desktop | <------------------> |   - VaultIndex    |--|   index     |
| (or any MCP    |                      |   - GitRepo       |  |   trash     |
|  client)       |                      |   - SettingsStore |  |   lance/    |
+----------------+                      |   - AuthStore     |  |   auth.json |
                                        |   - MCP server    |  +-------------+
                                        |   - RAG pipeline  |
                                        +-------------------+
                                                  |
                                                  v
                                        +-------------------+
                                        | LanceDB (vectors) |
                                        | Xenova / OAI emb. |
                                        +-------------------+

• Runtime: Bun

• Backend: Elysia + native FS + GitRepo (libgit-free shell wrapper with an async write mutex)

• Frontend: React 18 + CodeMirror 6 + unified/remark/rehype + highlight.js + KaTeX + mermaid (lazy) + Radix UI primitives + Tailwind tokens (CSS vars under the hood)

• Vector store: LanceDB (@lancedb/lancedb) per vault

• MCP transport: @modelcontextprotocol/sdk WebStandardStreamableHTTPServerTransport

• Auth: Bun.password (argon2id, no native build)

Per-component documentation lives next to the code; see docs/ for the MCP reference.

🛣️ Roadmap

• Daily-note templates with variable interpolation

• Snippet expansion in the editor (/ trigger)

• Hybrid search (BM25 + dense), fused via RRF

• Multi-vault support behind a single server

• Encrypted vaults (age key per vault)

• Docker image (multi-arch, < 200 MB compressed)

• Notarised macOS .app wrapping the binary

• Hosted read-only demo

Want to nudge one of these up the list? Open an issue or PR.

💖 Sponsor

brain.md is a solo open-source effort. If it's useful to you and you can chip in, sponsorship pays for the time that goes into new features, docs and review.

The Sponsor ❤ button at the top of this repo and the small heart in the brain.md topbar (next to About) both lead here.

🤝 Contributing

Contributions welcome.

1. Open an issue first for anything non-trivial — a quick design sketch saves a long PR rewrite.

2. Write the test before the implementation. Server tests run with bun test; the suite is currently 187 green.

3. Open a PR. CI runs typecheck (server + web) + bun test.

⭐ Star history

Found brain.md useful? A ⭐ helps other people running local-first agent workflows discover it. No newsletter, no tracking, no follow-up email — just a signal that this exists.

📄 License

GNU Affero General Public License v3.0 or later — see LICENSE.

brain.md is, and will stay, free / libre / open-source. The AGPL was picked over weaker permissive licenses for two specific reasons:

1. It closes the SaaS loophole. If you modify brain.md and run it as a network service for others — hosted, multi-tenant, rebranded, whatever — you must publish your modified source under the same AGPL. Strong copyleft for a server-side tool means the community always gets the improvements back.

2. It can't be relicensed under a permissive license downstream. Forks stay open forever. Nobody can scoop the project, slap a new logo on it, and ship a proprietary "Pro" cut.

You're free to:

• run brain.md, personally or commercially, without limits;

• fork, modify, redistribute, even rebrand — provided your fork stays under the AGPL and you publish the source you're running.

You're not free to:

• ship a closed-source product based on brain.md;

• host a modified brain.md as a public service without publishing your modifications under the AGPL.

Trademarks

The name brain.md and the brain.md logo are not covered by the AGPL. If you fork the project, you're welcome to do almost anything with the code — but please use your own name and your own mark for your fork so users aren't confused about which project they're running.

brain.md — your notes, your machine, your agents.

Built by Michał Lipiński  ·  github.com/mi4uu/brain.md  ·  report a bug