For one person who wants the work to carry on without them.
Latest release: NeuralVault 2.0 Beta, 15 October 2026. Expect bugs. Keep a backup of your vault. See what changed.
During the Beta everyone has Personal. In the next few weeks, when the Stable version is released, Personal becomes a monthly subscription.
Get notifiedNo subscriptions until the Stable version. No card, no obligation.One installer for every plan. Your account decides what you get: sign in and NeuralVault runs as Free, Personal or Business.
By downloading you agree to the Terms (version 2.6) and the Privacy Notice (version 2.5). This is a Beta: expect bugs, keep a backup of your vault.
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.
Sign in, and it unlocks
Personal is attached to your account rather than to the file you downloaded. During the Beta everyone has Personal, so signing in is all it takes. In the next few weeks, when the Stable version is released, Personal becomes a monthly subscription that you buy here or in the app, and we will tell you before it changes. There is no licence to install and nothing to paste.
What Personal costs
Four monthly plans with the AI included, each with the software inside. Prices are shown in your currency, and billed in pounds sterling.
- Software
- $10
- Usage balance
- $20
- Software
- $10
- Usage balance
- $40
- Software
- $10
- Usage balance
- $90
- Software
- $10
- Usage balance
- $190
Your own API keys, or a model on your own hardware? Personal on its own is $20 a month: the software and only that. The app contains no AI, and a model you bring is billed by your own provider. + tax where it applies. During the Beta everyone has Personal, and it becomes a monthly subscription in the next few weeks. See every plan in full
390+ models through one account.
With NeuralVault routing you pick a model from a catalogue of 390+ models and use it, with nothing to connect and no key to paste. Free works with your own API key or a local model. Personal does that and adds routing on top.
Your own key, or a local model.
- Cloud providers such as Anthropic and OpenAI, on your own API key.
- Local models through Ollama.
- Nothing is metered when you use your own key.
390+ models, nothing to connect.
- Everything Free does, your own keys and local models included.
- NeuralVault routing: choose a model from the catalogue, per model, in the picker.
- The NeuralVault AI score and our full model picker come with NeuralVault routing. With your own keys you get a plain model list.
- Routing is optional. Your own keys and a local model work without it. You can also use your own keys, such as OpenRouter, OpenAI and Anthropic, and that is free to use with your own keys. Routing makes it easier and nicer.
462 models were listed in the public OpenRouter model catalogue on 14 October 2026, and 393 of them can use NeuralVault's tools, which are the ones its model picker lists. Routing draws on that catalogue, so the number moves as it adds and removes models.
The file is free, and during the Beta so is Personal.
- Create your accountFree to create, and it is the thing Personal attaches to. You can do this before or after downloading; the order does not matter.
- Download the installerThe same file everyone downloads. There is no separate Personal build to hunt for, and if you already installed it you do not need to install it again.
- Sign in inside the appIt checks your account, sees Personal, and the paid rows switch on. Nothing to paste, no licence file, no key.
What Personal turns on
Personal unlocks the half of the application that runs on its own: a board agents work, a scheduler that starts jobs while you are away, and more than one model on the same question.
- A board your agents work themselvesA background runner takes the next card, hands it to an agent, and a second agent checks the result before it comes back to you.
- Work that starts without youA cron scheduler and file triggers, so a job can begin while you are asleep.
- Orchestra: several models on one questionPut more than one model on the same problem in a single run and compare what comes back, with the cost estimated before it starts.
See every capability, row by row, each marked with whether it works in the next release, is partly built, or is granted by your plan and not written yet.
Still decidingThe full case for PersonalWhat Personal covers, the four monthly plans with NeuralVault routing, why the software-only licence does not include a model, and how a working day with it goes.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. Windows is the main supported platform. There is no ARM build, and macOS and Linux are experimental (see below).
It installs for your user account only, so Windows never asks you for an administrator password. About 115 MB to download.
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. The first run needs a connection only to sign in.