SOVEREIGN BRAIN · HOMEPAGE · SHEET A-01 SCALE 1:1 · REV — WIP
Local · Private · Open Source

A local AI second brain
that runs on your machine.

Sovereign Brain is a private, offline AI assistant for your ideas — a self-hosted second brain powered by a local LLM. You talk; it captures and organizes everything into plain Markdown files that live on your disk. No cloud. No subscription. No one reading your thoughts but you.

FREE FOREVER · PUBLIC DOMAIN · WORKS OFFLINE
A hand-drawn brain on a laptop — a local AI second brain
FIG. 01 — the brain, drawn on your machine NOTHING LEAVES THIS FRAME
YOUR MACHINE · 100% LOCAL · OFFLINE
A·02 · SEE IT IN ACTION

Watch a real session

A real terminal session onboarding on my laptop, played back at 2×.

TERMINAL — pi @ sovereign-brain 2× · LOCAL

100% private

Runs fully offline on local inference. Nothing is sent to any server, ever.

Plain Markdown

Every note is a .md file you own — open it in Obsidian, VS Code, or any editor.

Agent-driven

Just talk. The agent summarizes and files key ideas, so capture is frictionless.

Free & open

Public-domain template. No lock-in, no account. Fork it and make it yours.

A·03 · HOW IT WORKS

How your local AI second brain works

STEP 01

You dump

Thoughts, ideas, TODOs — throw them in freely. The agent automatically organizes the information into simple Markdown files.

STEP 02

Brainstorm together

You and the agent work through problems together, leveraging your existing context to develop real plans.

STEP 03

You execute

You know what to work on — the minimum work required for maximum return — and can quickly iterate.

A·04 · INSIDE THE TEMPLATE

What's inside the template

A clean, ready-to-run structure your AI agent already knows how to use.

FILE TREE — sovereign-brain/PUBLIC DOMAIN
sovereign-brain/
├── AGENTS.md          # how your AI agent reads + grows the brain
├── references/        # who the agent is + what it's for
│   ├── purpose.md
│   └── personality.md
└── workspace/         # your living knowledge
    ├── daily-thoughts.md
    ├── todo-upcoming.md
    ├── new-project-ideas.md
    ├── project-history.md
    ├── projects/
    └── sessions/         # summarized brainstorms, dated
A·05 · REQUIREMENTS

What you'll need

Sovereign Brain runs a real language model locally, so it's built for people who want full privacy and own capable hardware.

DRAWING NOTES — REQUIRED SETUP
01 · HARDWARE
A machine with combined RAM of atleast 32 GB to run a local model.No capable machine? Run it on a more private cloud (PPQ.ai TEE) instead.
02 · INFERENCE
A local inference setup — llama.cpp plus an open model - Qwen3.6-35B-A3B
03 · AGENT
An agent harness to drive it — the pi agent.

NEW TO LOCAL AI? SEE HOW IT WORKS ABOVE, OR THE BLOG FOR SETUP GUIDES.

A·06 · COMMON QUESTIONS

Common questions

Is my data private?

Yes — it runs offline on your machine, nothing is uploaded to any server.

Does it cost anything?

No. The template is free and released into the public domain.

Can I use my own editor?

Yes — it's plain Markdown, so Obsidian, VS Code, and any editor work.

How is it different from ChatGPT or Notion AI?

Those run in the cloud on a subscription. Sovereign Brain runs locally, keeps data on your disk, works offline, and costs nothing.

A·07 · FROM THE BLOG

From the blog

A hyped AI robot on a launch stage surrounded by benchmark charts, stuck in a loop amid mismatched filenames JUN 04
2026
Gemma 4 12B: All Hype, No Substance
Comparing small local language models for a private AI second brain JUN 01
2026
Best Small Local Models for Your Sovereign Brain
A laptop flexing muscular arms — local AI getting strong enough to run on your own machine JUN 01
2026
Is 2026 the Year of Localmaxxing?
All articles →
Project
Sovereign Brain — Homepage
Sheet
A · 01
Scale
1 : 1
Revision
Hi-Fi · Direction A