Cortex gives memory to the AI agents you already use.

You work with Claude Code, Codex, ChatGPT. Every session starts from nothing: you explain the context again, you repeat decisions already made, you redo trade-offs already settled. The model changes, and everything you built with the previous one stays behind.

Cortex captures the work you carry out in those tools, builds an experience from it, and returns the relevant context when they need it. It replaces nothing. You keep talking to your agents exactly as you do today, and Cortex runs underneath.

What it keeps

Remembering is not rereading. Cortex does not replay your old conversations. It extracts what carries forward: decisions and the reasons behind them, constraints, questions left open, what worked and what failed.

Every item keeps its provenance, its scope and its state. A conclusion established six months ago may have been contradicted since; it stays readable, but it loses the right to influence the present. Something learned on one project does not spread to the others on its own. Archiving is reversible, forgetting is not, and that last gesture asks for a written confirmation.

Work is organised into workspaces and topics. A topic carries its own memory. What follows you from one topic to the next, your methods, your constraints, the way you work, lives separately.

You decide what goes in

A session enters Cortex only if you allow it, and you can take that permission back. A learning Cortex has inferred waits for your approval before it can weigh on anything; you can then dispute it, remove its influence, or erase it.

Three levels of control: bring everything back to me, apply what is safe while flagging the rest, or apply everything and leave only the trace. Whatever the level, the irreversible stays human, and everything applied stays traced and revocable.

On your machine

Cortex runs locally. Semantic search relies on a model that lives on your Mac. No remote telemetry.

For its own processing, Cortex needs an engine. It plugs into a subscription you already pay for (Claude Pro or Max, ChatGPT, Z.AI, Kimi) or into a pay as you go API key. Ollama works too, if you would rather nothing left the machine at all.

That processing is spread across about twenty workers sorted into three tiers: routine operations, the consolidation core, and genuinely complex analysis. Each tier runs on the connection you assign to it, with a fallback order if that connection drops. So you choose where the effort goes, and what it costs.

What it is not

Not another chat, not another agent. You do not talk to Cortex: it is a system, not an interlocutor. It is not a memory that learns quietly either, with no way for you to see or correct it. The agent tier, the one that works and acts on the same memory, is called Cortex.deck and plugs in on top.

Where it stands

Private beta on macOS, priority access on request. Installation takes about ten minutes, most of it downloading: Cortex ships its own tooling and its own model, in its own corner, without touching what you already have installed. First run configuration fits in seven screens, two of which ask for a real decision.

Two caveats I would rather state than hide. The app is not signed by Apple yet, so macOS shows a warning on first launch. And on the browser extension, capturing ChatGPT, Claude.ai and Gemini conversations works, but returning memory into the web page is not live yet.

Under the hood

A Tauri app, Rust on the system side, React and TypeScript on the interface, with signed automatic updates. The site and API run on Astro as a static build, Fastify and PostgreSQL, deployed in containers behind Caddy.