An app you install on your own computer, where AI agents do real work for you instead of just answering questions. It remembers how you work, so you explain a thing once rather than every morning.
NeuralVault is a desktop application. You open it, point it at a folder of your own notes, and that folder becomes what it knows. Then you stop typing questions and start handing out jobs: read the last month of support email, work out what keeps coming up, write it up and leave it on the board for me. It goes and does that, and comes back with the work and a record of how it got there. The trade calls this an agent harness. What it is for is simpler.
You explain your project, your stack and the way you like things done. Tomorrow you open a new chat and explain all of it again.
It keeps what it learns as plain Markdown on your own disk, so you say a thing once.
Getting a useful answer means pasting your work into someone else’s browser tab.
It works on your own material where it sits, and nothing leaves the machine without you approving it.
It answers, and then you still do the work. Every single step goes back through you.
You hand it a job instead of a question. It splits the work, runs to a schedule, and reports back.
When it does act on something, you cannot see what it touched or undo it afterwards.
Every tool call is logged and every file write is a checkpoint you can rewind to.
The problem with agents is rarely the model. It is the agent inventing a tool it does not have, forgetting on Tuesday what you told it on Monday, and being impossible to leave alone with anything that matters. Those three failures are what the three below are answers to, and each one comes from how NeuralVault is built rather than from a feature that could be added to anything else next quarter.
Any major cloud provider on your own key · or a local model, if you want one · keys held in Windows Credential Manager, never a plaintext file
Most of the field rents you a model in somebody else’s cloud, and your material has to travel there for anything to happen. This installs on your computer, and the model is your call: a cloud provider on your own key, a model running locally, or one of each depending on the job. Either way its memory is a folder of Markdown files on your own disk.
An agent’s rules are Markdown you can edit · audit log and run ledger on every tool call · byte-exact checkpoint on every file write
Every agent works to a rule set written in plain Markdown: what it is for, which tools it is allowed to use, and which folders it may touch. Those files are yours to open and edit. What it remembers is a note. What it did is a log. There is no opaque config and no hidden state, which is the thing that makes handing it real work reasonable rather than reckless.
A shared board · a workflow builder over plain Markdown · an approvals queue · a calendar · a screen recorder · voice memos
The harness is the product here rather than a feature added to a code editor. So it is equally at home on research, client files, contracts or a decade of notes, and there is somewhere for the work to live once an agent has done it.
This is the difference between asking an AI something and giving it a job. All four are the harness itself, so all four are true across every edition.
Agents get a defined set of things they can reach, and nothing outside it. You decide what is on that list.
It does not start cold every session. What it learns about how you work is kept, and it gets sharper the longer it runs.
Reading is usually open. Anything that changes something, spends money, or leaves your machine stops and waits for you.
Every action is written down. You can go back and see what ran, when, and why it decided to.
Not the category, the software. Every surface named below is one that ships today, and they are named rather than described so you can check them against the product instead of taking the sentence on trust.
It reads what you have written and answers out of it, pointing at the note the answer came from rather than producing something plausible. The search is hybrid, so an exact string and a vague description both land.
Agents are files you can open and edit. Give one an objective and it breaks the work across sub-agents of its own, sees which tools each may touch, and iterates over what actually failed rather than stopping at the first error.
Six columns, To Do through Done, shared between people and agents. An agent picks up a card and moves it across on its own. Only a person closes one.
Work on a schedule, or triggered by a file changing. It does not need you sitting in front of it for anything you have already approved the shape of.
Record yourself doing a thing and it becomes a procedure the agents can run afterwards. Talk at it when writing is slower than speaking, and draw at it when neither is fast enough.
Every file write is a checkpoint you can rewind to. Being able to undo it is what makes letting it run in the first place reasonable.
Every product page tells you what a thing does. This is the other half: what is true today, what is not finished, and what happens to your material if you try it and walk away. A teal marker is live now, a purple one is dated below.
The build targets the Windows installer and nothing else. There is no macOS or Linux version, and none is being built right now.
An early release, in active development. Things move. Keep your own backups of your notes and do not make this the only copy of anything you cannot lose.
It is not signed yet, so Windows will call the publisher unknown on first run. Choose More info, then Run anyway. Nothing is wrong with your machine and nothing is wrong with the file.
Use a cloud provider with your own API key, or run a model locally through Ollama, or mix the two per job. Neither is the default and neither is required. Whichever you choose, the key is yours and Windows holds it rather than a file on disk.
Point it at a folder and it reads and writes that folder in place, as Markdown. No database and no import step, so there is nothing to export if you walk away. The folder was always yours.
No telemetry and no usage pings. A crash writes a log on your own machine and stops there. If you send us a bug report, you see the exact text first and press submit yourself.
Team channels and email come into the app, and a drafted reply waits in the approvals queue. There is no outbound sending from the app yet.
Personal is a flat monthly price, in full on its own page. Business is priced to the size of the deployment and how much of it you switch on, then quoted after a free consultation. Free is the same build with the paid parts locked.
Vault memory, the agent fleet, the board, the approvals queue, checkpoints and the audit trail. Running today, in beta.
The chat-first build is public. One installer, no account, and the paid rows locked rather than removed.
The full harness unlocked, and API credits included, so you can use a cloud model without opening provider accounts and managing keys yourself.
The sync server, per-user accounts, role-scoped agents and the connector timeline, installed on hardware we specify and keep running.
Dates are what we are working to, not a contract. This is a small company shipping a beta, and a date that slips will be changed here rather than quietly left up.
Each card adds to the one before it. 19 capabilities were compared head to head and a typical harness has 8 of them. The bars run wider than the lists because they measure NeuralVault's whole surface, 64 things, 39 of them in Personal. The 45 outside the compared 19 were never assessed against another product, so read the pale stretch of the first bar as unmeasured, not missing.
of 64 capabilities
The baseline the other two are measured against.
All 11 of them, most consequential first. That is 11 of the 19 capabilities this page compares. The other 45 in the bar above were never assessed against another product and are not being claimed as gaps.
of 64 capabilities
Everything in the first card, and then:
The complete harness. Nothing here is held back for a higher tier.
of 64 capabilities
Everything in Personal, unchanged, and then:
The same engine as Personal, pointed at running a company instead of a codebase.
Each page ends with what that edition costs. Personal is a flat monthly price you can see in full; Business is priced to the size of the deployment and how much of it you switch on, and quoted after a free consultation. Free is the same application with the paid capabilities locked, so trying it costs nothing either way.
This is not a lite version and a pro version. Personal is the complete harness with nothing held back: the same agents, the same memory, the same audit trail. Business takes that exact engine and adds what stops being optional the moment other people depend on your output. So the question is not which product is better, it is whether you are running a codebase or running a company.
The full harness, on your machine, with no subscription and no per-token bill.
Put as much of your own material into it as you like. What it learns is written to your own disk as plain Markdown you can open, edit and back up, not to a row in somebody else's database. Run the model locally too and none of it leaves the machine at all.
Not only for code. Point it at research, client files, contracts or a decade of notes: anything you would rather not paste into a browser tab.
Everything in Personal, unchanged, and then the layer a company needs around it.
The difference is not more features, it is that the work stops being yours alone. Other people can see it, act inside it and be held to what they may touch, and every one of those actions leaves a record. That is the part nobody needs on their own machine and nobody can run a company without.
Both pages end with what that edition costs. Free is on general download now.
The editions page puts Free, Personal and Business in one row with what each one gives you and what it costs, then a section on each. It is the shorter way to place yourself than reading two product pages to find out which one you are.
Compare the three editions