SILICON CORTEX · USER-OWNED COGNITION

Your vault got bigger.
Your projects didn't.

You have the system, the plugins, every note you ever took — and you still spend the first twenty minutes of every AI session explaining where things stand. Silicon Cortex keeps one continuously-updated, human-verified picture of your work in plain Markdown on your own machine, so Claude, ChatGPT, Codex and Cursor all start where you left off. Nothing resets. Everything compounds.

The Gumroad founding presale has ended. No purchases are available through this site.

Product vision · 59 seconds: user-owned project memory, human approval and traceable decisions. Illustrative scenario.

📁 Plain files · readable forever 🔑 Your API key, your files 🚫 No app · no account · no lock-in 🇬🇧 UK patent application filed
The problem

You don't have a memory problem. You have a context problem.

If you run several serious things at once — a company, a product, a creative practice — and you work with more than one AI, you already know the tax: every new chat starts from zero. You re-explain your project, your constraints, your history. Again.

Claude doesn't know what you told ChatGPT. Codex starts from nothing. The smarter the models get, the more this one bottleneck costs you. You've become your own context clipboard.

The system

Capture once. Every AI you use gets the context.

🗂A clean vault structure

Organise life and work as long-running tracks — a business, an album, your health — instead of a folder graveyard.

🤖Keeper, a tiny assistant

One Python file, zero dependencies, bring your own key. Turns quick captures into structured, traceable memory, keeps a live dashboard of focus and open loops, and answers questions about your own history.

⚡️Agent-native from day one

Ships with CLAUDE.md / AGENTS.md guides. If you already use Claude Code or Codex, your agent reads your vault natively and writes results back in.

✅Drafts, never overwrites

Nothing enters your confirmed memory until you approve it. Every summary is auditable back to its sources. Your AI can propose; only you decide what's true.

🔒Privacy gate on every command

Anything you tag sensitive is held back from cloud models by default. Plus a daily spending cap — a background assistant never surprises you with a bill.

🪶No app. No account. No lock-in.

A folder you own — readable in any editor, greppable, git-able, Obsidian-compatible. If we disappear tomorrow, your memory doesn't.

The rule at the heart of it

Most AI memory tools make the model's guesses your ground truth. This does the opposite.

RAW INPUT

Immutable.What you captured is never rewritten by a machine.

MACHINE OUTPUT

Always a draft.The AI proposes structure, summaries, connections — nothing more.

CONFIRMED MEMORY

A separate layer only you can write to.Slower by design. Still readable and trustworthy 12 months in.

That's the whole product.

Built honest

Built from the system the founder uses daily.

🇬🇧Patent-pending

The architecture is the subject of a UK patent application, filed June 2026.

🛠Run daily, for real

A company, a music practice, and this product itself are operated on this exact system every day.

🕵️We can't see anything

Cloud calls go only to your chosen provider with your key. The vault never leaves your machine. We run no servers.

Project update · October 12, 2026

The Gumroad founding presale has ended.

Silicon Cortex remains the founder's focus. The earlier Lite presale, pricing tiers, seat limits, delivery dates and promotional offers are no longer available.

This site now provides background on the system and its principles. There is no active purchase offer or new delivery commitment on this page.

Fit check

Built for people who run everything with AI.

✓This is for you if…

  • You're a founder, indie hacker, researcher or creator doing consequential, long-running work
  • You use more than one AI seriously — Claude, ChatGPT, Codex, Cursor…
  • You're done being your own context clipboard
  • You want your memory in files you own, not someone's database

✕This is not for you if…

  • You need team features — this edition is single-user
  • You want a polished GUI app — this is a folder + a CLI + your existing agents; that's the point
  • You won't spend $5 of API credit
FAQ

Questions, answered straight.

What is Silicon Cortex, in one sentence?

Silicon Cortex is a reliable cognition layer that lives on your machine, in plain Markdown, and gives every AI you use — Claude, ChatGPT, Codex, Cursor — the same continuously-updated, human-verified picture of your work. No app, no account, no lock-in.

Do I need to know how to code?

No — if you can open a terminal and paste three commands, you're in. A full install guide is included, written for humans.

What does it cost to run?

Your own API key. Typical daily use is cents, not dollars, and Keeper has a built-in daily spending cap.

Which models work?

OpenAI and Anthropic out of the box; the provider is a one-line config field. Or skip API keys entirely and use your existing Claude Code / Codex subscription as the engine.

Is my data private?

The vault is plain files on your disk. Only what you choose to process is sent, only to your provider, and anything tagged sensitive is held back by default. Nothing touches our servers — we don't have servers.

Mac only?

macOS and Linux natively; Windows works via WSL.

Is the founding presale still open?

No. The Gumroad founding presale has ended. Previous prices, delivery dates and promotional offers are no longer available.

Stop re-explaining your life to machines.

Silicon Cortex remains focused on context that users own and control.

Contact the founder