Setup Guide
Install Cerebro in under a minute. One installer, one CLI, done.
1Prerequisites
The only third-party requirement is the Claude Code CLI. Everything else is bundled inside the installer.
- Claude Code CLI
Any Claude subscription tier works. Install from docs.claude.com. Cerebro uses your Claude Code login — zero extra API cost.
- Windows 10/11 or Linux (x64)
macOS coming soon. AppImage runs on most modern distros.
- 4GB+ RAM, 500MB Disk Space
More RAM recommended if you enable local embeddings.
2Install in Four Steps
Download the installer
Grab the latest release from GitHub. Pick Cerebro-Installer.exe on Windows or Cerebro-Installer.AppImage on Linux.
Run the installer
On Windows, double-click the .exe and follow the wizard. SmartScreen may ask you to confirm — click More info → Run anyway (Cerebro is open source and isn't code-signed yet).
On Linux, chmod +x Cerebro-Installer.AppImage then double-click or run it from a terminal.
Sign into Claude Code
If you haven't already, install the Claude Code CLI and log in. Cerebro detects your session automatically.
# Install Claude Code (if you haven't)
npm install -g @anthropic-ai/claude-code
# Sign in
claude loginActivate (Pro only)
Pro and Pro+ subscribers paste the activation code from the dashboard into Cerebro on first launch. Free tier has no activation step — you're already done.
That's it. Open the app and Cerebro is live. The 49-tool brain auto-registers with Claude Code on first run.
3Optional: Multi-Machine Memory
Want one shared memory across every device you use? Point Cerebro at a NAS-mounted folder.
Shared NAS storage
Recommended for power usersWhat you need
Mount the share
# Replace YOUR_NAS_IP and the share name with your own
sudo mount -t nfs YOUR_NAS_IP:/volume1/AI_MEMORY /mnt/nas
# Or persist via /etc/fstab:
# YOUR_NAS_IP:/volume1/AI_MEMORY /mnt/nas nfs defaults 0 0:: Map a network drive (replace with your NAS IP / share)
net use Z: \\YOUR_NAS_IP\AI_MEMORY /persistent:yesPoint Cerebro at it
Open Cerebro → Settings → Storage. Set the storage path to your mounted share (e.g. /mnt/nas/cerebro or Z:\cerebro). Repeat on every machine. They'll all read and write the same memory database — no sync needed.
4The Creator's Setup
Reference architecture for the home lab Cerebro is developed against. You don't need any of this — Cerebro runs great on a single laptop. This is what happens when you go all-in.
A laptop is enough. The full home lab is for distributed embeddings and 24/7 agents. The same installer powers both.
5What Cerebro Does NOT Require
Common assumptions that are wrong — Cerebro is simpler than you think:
- No Docker
v6 ships as a native installer with the runtime bundled — no containers, no Compose files
- No Python or pip
The installer brings its own runtime — nothing for you to install
- No API keys
Uses your Claude Code subscription directly
- No cloud account
100% local — your data never leaves your machine
- No database server
Built-in SQLite + FAISS, zero config