The whole application, with the paid rows locked rather than removed.
This is the same installer every edition uses. It runs as Free until an account says otherwise, so this is the file to take whichever edition you end up on.
The installer is code-signed by Perpetual Technologies AI Ltd. Windows may still show a blue “Windows protected your PC” panel while a new certificate builds reputation: choose More info, check the publisher it names, then Run anyway.
Nothing to activate
Install it and open it. There is nothing to buy, no card, and no expiry.
No account, no card, and nothing expires. It is not a trial.
Three steps, none of them a payment.
- Download itThe installer above. Nothing to buy and no card, and it does not expire.
- Open it and sign inAn account is free to create. It is what tells the app which edition you are on, and on Free that answer is simply Free.
- Point it at a folderYour vault is a folder of Markdown on your own disk. Pick an existing one or let it make you a new one.
What you get for nothing
Free is not a trial and it does not expire. It is the same build the paid editions run, with fewer switches on, so nothing you learn using it is wasted if you move up later.
- Chat with Cortex over your own vaultYour notes stay as plain Markdown on your disk, searched by keyword and by meaning at once.
- It can write to your vault, and you approve each changeEvery write waits on a card showing which files it touches until you approve it, and one control undoes it afterwards.
- Any model you likeA local model through Ollama, or Anthropic, OpenAI and others on your own API key. No gate on either.
See every capability, row by row, each marked with whether it works in this build, is partly built, or is granted by your plan and not written yet.
Still decidingRead what NeuralVault actually doesThe full picture: what it is for, how a session goes, what it deliberately does not do, and where your material lives.Read the full pageWhat it needs to run
Free, Personal and Business are the same application with a subscription between them, so the machine needs the same things whichever one you end up on.
Windows 10 or 11, 64-bit. There is no macOS build, no Linux build and no ARM build.
About 115 MB, and it installs for your user account only, so Windows never asks you for an administrator password.
The light way to run it. The model does its thinking on your provider’s hardware, so your machine only has to run the app.
Much heavier, and worth knowing before you start. Ollama holds the whole model in memory for as long as it stays loaded.
The one local-model number worth having in advance: the model our getting-started guide suggests, qwen3.5:9b, is a 6.6 GB download, and a smaller model costs you proportionally less. We do not publish a minimum memory figure, because with a cloud provider the app is the only thing running on your machine and with a local model it is the model that decides, not us. The app carries its own browser engine, so setup fetches nothing else, and the first run needs a connection only to sign in.