BetaDuring the Beta everyone has Personal. In the next few weeks, when the Stable version is released, Personal becomes a monthly subscription. We will tell you before it changes.
A desktop app that runs a fleet of agents. Graph everything you know into local memory, give Cortex an objective and let it split the work across agents that iterate rather than stopping at the first attempt, and keep every byte on the computer in front of you. Free is available now as a Beta. Public early access.
Personal is all your AI bills in one place: we handle the billing, the routing and the backups, and routing is only available through Personal.
The full NeuralVault harness for one person: agents, a board and schedules.
Who it is for
Developers and power users who want agents to work while they are away.
What it costs
From $20 a month. Free to use during the Beta.
Available now?
Yes, in the Beta.
Platform
Windows.
What It Is
A desktop app that runs a fleet of agents.
Concretely: you download an application and install it, the same as any other desktop program. It opens on a dashboard. One of its tabs is a chat with Cortex, the assistant that runs the place, and the rest are the screens where the actual work happens.
Underneath that, it graphs what you know, holds what it learned last week, and dispatches sub-agents to do the jobs you hand off. All of it on the machine in front of you.
It is an app, not a service. A desktop build with its own bundled runtime, not a page you sign into on someone else's server.
Its memory is a folder of Markdown. Plain notes on your disk that you can open, edit, diff and back up without the app running.
You choose where the model runs. A cloud provider on your own API key, or a local model through Ollama on your hardware, or both depending on the job. Neither is the default.
Cortex assigns the work and everything reports back up to it, so nothing runs unwatched and you are only asked when the decision is actually yours. They all read from memory and save to it, which is why what one run works out is there for the next. Nothing here leaves your computer unless you connect an outside model and allow it to.
What It Actually Does
Seven things it does that a chat window cannot.
01
Indexes what it knows
Every note is a node and every link between them an edge, so search follows the connections you have written. There is no map view to look at yet. Answers cite the note they came from.
02
Splits work across sub-agents
Hand a job off and the agent taking it decides whether it needs breaking up, then spawns sub-agents for the pieces. You see which tools each may touch, and a card shows exactly what it will write and which files it touches before anything is saved.
03
Scopes what tools it can reach
Agents get a defined set of things they may touch and nothing outside it. You decide what is on that list before anything runs.
04
Keeps a record of every action
What ran, when, and why it decided to. When something changes unexpectedly, there is a trail rather than a shrug.
05
Holds a memory that survives restarts
What it learned about your stack last week is still there this week. It gets sharper the longer you run it, without manual retraining.
06
Runs the model wherever you want
Use an outside API while you evaluate it, then move the model onto your own hardware and cut the last thing that leaves the machine.
07
Iterates instead of stopping at one attempt
It makes the change, runs the suite, reads what actually failed and goes again, up to a bounded number of rounds. You get the result of a loop rather than a first draft, and it stops on its own rather than running away with your machine.
How The Fleet Is Organised
Cortex gives the orders. Everything reports back to it.
This is the part that makes it a harness rather than a chat window. You are not managing a list of bots. You brief one controller, it works out who does what, and the results come back up to it rather than landing in your lap piece by piece.
Tier 1
Cortex, which runs the place
The assistant in the chat tab is also the controller. You give it the objective, it decides which agents the job needs, hands them their share of it and watches what comes back. You are talking to the thing in charge rather than to one worker among many.
Tier 2
Agents, held to what they were given
An agent carries its standing instructions, the tools it may call and the folders it may touch, in a configuration you can open and read rather than a hidden registry, so an agent that behaves oddly is something you can inspect.
Tier 3
Sub-agents, spawned by the agents themselves
Delegation is a tool an agent can call, so an agent handed something large breaks it up and hands the pieces down to sub-agents of its own. Each inherits a narrower scope than its parent, never a wider one, and reports its result back up the chain rather than off to the side.
Decisions climb the same chain the work came down. A sub-agent that needs a call asks the agent that gave it the job. That agent settles what it can and passes up only what it cannot. Cortex does the same, and puts something in front of you when the answer is genuinely yours: an executive call, a judgement it should not be making alone, or a case where it is simply not sure. The point of the hierarchy is that you are the last resort rather than the first interruption.
Underneath all of it: every agent is held to the tools and folders it was given, every call it makes is written to an audit log and a run ledger. Files are snapshotted before a write you approve in chat, and one control puts them back; a write made by a scheduled agent run is captured but has no restore control yet. Agents can propose edits to their own instructions, and those proposals never take effect on their own: they are held on disk, and the screen for reviewing them is not built yet.
More Than One Model
A second pass checks the answer.
You are not locked to one model, and you are not limited to one at a time. Run any Ollama model locally, point it at any OpenAI-compatible endpoint, or add an API key for any cloud provider at all, then choose per role which model does what. There is no approved list: if it has an API, it can take a seat.
Check-work adds a second pass over an answer. It reads the answer in a fresh context, without the conversation that produced it, and looks for what is wrong. You get the answer and the critique together, so you can judge the check as well as the work.
01
One model answers
Whichever model you assigned the role does the work and gives its answer.
02
A second pass is handed only the answer
Not the conversation, not the reasoning behind it: the answer on its own, and one instruction, find what is wrong with it. Unsupported claims, plain errors, parts of the task it skipped, anything that would break if you acted on it.
03
You get both back
The answer and the critique together, so you can judge the check as well as the work.
What Personal adds
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.
NeuralVault Free
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.
NeuralVault Personal
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.
In developmentRouting is partly built: models answer today, and the billing half has not been proven end to end.
BetaNeuralVault routing runs on a prepaid usage balance, and the balance opens soon. During the Beta everyone has Personal.
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.
A Session, End To End
What using it actually looks like.
Not a feature list. This is the loop you are in most days, and every step of it happens without your code leaving the machine.
01
Point it at your notes
It graphs them into local memory: every note a node, every link an edge. Nothing is uploaded; the index lives beside the files.
02
Ask it something real
Not "explain this file" but "where does this break". It answers from the graph, with paths and call sites you can open.
03
Give it the whole job, not one edit
Not "change this line" but "fix every call site and get the suite green". Cortex assigns it, the agent splits it across sub-agents, and it works through what failed rather than stopping at the first attempt.
04
Approve, or send it back
Nothing lands without you. Reject it and the correction goes into memory, so the next attempt is better.
Choosing A Model
Our routing, or your own keys.
One dialog lists the models. You pick where each chat goes, and you can change it any time. The NeuralVault AI score and our full model picker come with NeuralVault routing. With your own keys you get a plain model list. 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.
1
Search
Type a name, a maker or what you want it for.
2
Pick a route
NeuralVault routing is the model we serve for you. My own keys is your key, or a model on this PC. The switch shows once you have one.
3
Read what it can do
Each row shows if it sees images, uses tools and thinks first. A dashed box means the provider does not say.
4
Star the ones you use
Starred models get their own Favourites group at the top.
!
NeuralVault routing is partly built. Your own keys and local models work today.
Chat
Choose a model×
1Search models by name, maker or use
2NeuralVault routingMy own keys
Filters
Model3Can
4Favourites
★
Everyday modelQuick answers and tool use
All models
☆
Careful modelThinks before it answers
☆
Image modelReads pictures and documents
☆
Small modelLight and fast
Does itDoes notNot publishedSees images, Uses tools, Thinks first
An illustration of the model dialog, with generic model names and made-up content, not a screen capture.
The Rest Of The App
Coding is the hook. This is everything else you get.
Personal is not a code assistant with extras bolted on. It is the whole application, and the repository work above is one of the things you can point it at. These are the other screens, all of them included, none of them an upgrade.
Chat
Conversation with Cortex, the resident assistant. History, and rolling compaction for long chats.
Board
A kanban you and your agents both work. Agents pick up cards on their own; only you move anything into Done.
Memory browser
Your notes as they are on disk. Plain Markdown, wikilinks and frontmatter included, editable outside the app.
Dashboard
Memory stats, activity, fleet status and open tasks. Every figure is a live read of a real file, never an invented number.
The `nv` CLI
The same agent Chat runs, headless: nv run for a scripted turn, plus board, search, notes, sessions, audit, orchestra, connectors, projects, plugins and settings, all from a terminal. No window, so it drops into CI, cron, or a shell script.
Trust And Memory
Checkable, and it remembers what you tell it.
How it earns your trust
Every step is on the record, and nothing is written without your yes.
A harness is only worth running if you can see what it did and stop it doing more. These are the mechanisms, each stated with its limit.
Every tool call is logged
What ran, whether it was allowed, and what came back are written to an audit log and a run ledger on your disk. The audit log is readable on every edition, Free included.
Approval cards before any write
When Cortex asks to create, append to or move a note, a card shows what it asked for and which files it touches, and nothing happens until you approve. Deletions are refused outright.
Undo, with a stated limit
An approved write is snapshotted first and one control puts the files back. It restores the files an approved chat write touched, not the conversation: the transcript still shows what was written.
In developmentCovers approved chat writes only. Scheduled agent runs capture a snapshot but have no restore control.
Each model says what its vendor does with your data
The model catalogue shows capability scores beside a per-vendor data-handling label, on every edition, so the choice rests on the facts and not on the brand.
Your balance is metered by rules you can checkEach routed call is charged at what the provider reported it cost, the balance stays on screen while you work, and the monthly allowance is stated to expire. The mechanism is built; the billing half has not been watched end to end yet. Buying usage from us opens soon. How the balance is counted.
What we countNeuralVault sends anonymous app-health and usage counts so we can check every feature works and spot sudden spikes. No conversations, notes, file names or account details, and nothing that identifies you or your machine.
The memory that stops you repeating yourself
Tell it once. It is read back into every later conversation.
“Remember that”
Say “remember that I prefer short answers” and the fact is written to a durable profile that is read back into every later conversation. The write waits on your approval.
“From now on”
A standing rule is appended to your own CORTEX.md, the file Settings shows you, so you can read it, edit it or delete it. It also waits on your approval.
A vault it searches
Your notes are plain Markdown on your disk, searched by keyword and by meaning together, and read back into the conversation when they are relevant.
For Developers: Scripts, CI And Cron
There is also a CLI.
nv: the same fleet, headless, every other command surface beyond run. Every tool is denied unless you allow it. Part of Personal, not a separate purchase, and not in a public download yet.
In developmentBuilt, tested and gated to Personal. It is not in any public download yet.
Illustration
# the same agents and memory as the app, headlessPS> nv search launch plan
# notes matching, best firstPS> nv audit
# what ran, when, and whyPS> nv board
# the pipeline boardPS> nv run <prompt> --json
# one turn, one event per line# tools denied unless you allow them# exit code 5: a tool was refused
Illustration. These are real nv commands, shown without output. The CLI is built and tested and part of Personal, and it is not in a public download yet.
Why It Is Different
Three things a browser tab cannot offer, and nothing you have to give up for them.
01 · What you gain
Things a tab in your browser will never do.
It stays on your machine
The app, the graph and everything it remembers sit on your own computer. Run the model locally too and no external provider ever sees a line of your source.
It remembers you
Not just the current conversation. Corrections stick, context carries between sessions, and it stops re-learning your stack every morning.
It is yours
On your own API key or a local model, nothing from us is metered while you think, and no provider swaps the model underneath you mid-project.
02 · What you keep
It reads the setup you have already written.
If you have spent months tuning standing instructions, skills and slash commands for another agent, none of that is wasted. Point NeuralVault at the same folder and it picks them up untouched. No migration, no second file to maintain, nothing to rewrite in a proprietary format.
CLAUDE.md
Standing instructions read as written, up to 12,000 characters, and exactly one file per directory so nothing is injected twice.
AGENTS.md
The same idea in the AGENTS.md format. A project set up with one runs here with no second file to maintain.
*/SKILL.md
Skills discovered in the standard folder layout. The ones you have already written are found and read, not re-declared.
.claude/commands/
Slash commands picked up from the same place they already live, right beside your skills.
MCP servers
Add the servers you already run through the connector catalogue. Their tools arrive as tools, inside the same permission model as everything else.
CORTEX.md
The one that is not optional. It is what tells the model how NeuralVault itself works, and it gets its own section below.
Your instructions, your skills, your commands, and the MCP servers you add. What changes is underneath them: memory that survives the session, permissions on every action, and a record of what ran.
The One File That Matters
CORTEX.md is how it knows what it can do.
A CLAUDE.md by another name, after the assistant that reads it. The difference is what goes in it. Instructions for a coding agent say how you like your code. This says how NeuralVault works, and it is what turns whatever model you point at it into something that can operate the place.
CORTEX.mdRequiredSix core sections
How to save
Where a note belongs, how it gets linked, what has to be written down and when.
How to use the features
Driving the board, approving a write, using the tools it has.
How to delegate
When to split a job across sub-agents, and when to escalate instead of guessing.
House rules
How it should speak, what it must verify before saying it, and what it must never do alone.
Where things live
Which paths matter, what belongs in each, and the directories it should never touch on its own.
How long it can be
Up to 12,000 characters, and exactly one instruction file is read per directory, so every line in it has to earn the space.
Edit it freely, that is the point. Just do not delete the core sections: they are what tell the model these capabilities exist. Strip them and you keep the features while losing the thing that knows how to use them.
Already have a CLAUDE.md?
You are most of the way there. NeuralVault reads Claude Code's CLAUDE.md as written, so a project you have already tuned works on day one. It just works better converted, because a CLAUDE.md says nothing about NeuralVault: it was never written for it. Left as-is, your rules get followed by a model that does not know the board or the approval cards exist.
The conversion is one instruction: ask Cortex to read your CLAUDE.md and write it out as a CORTEX.md, keeping your rules and adding the core sections.
One thing to know first
Exactly one instruction file is read per directory and CORTEX.md is checked first, so adding one does not stack on your CLAUDE.md, it replaces it.
Convert rather than copy, or rules you spent months on quietly stop being read.
Personal Not Enough?
Business has all of this, and a great deal more.
Not two products, and not a trade. Business is this same application with the company parts switched on. Nothing here is removed or held back: every screen, every agent and every capability on this page is in Business too. What it adds on top matters the moment other people start depending on your output.
NeuralVault Personal
The whole harness. Agents, persistent memory, the board, approval before each write, and the audit trail. Local models and the plugin API. Sync across your own devices is in development. Of the connectors, the six named sources (Shopify, YouTube, Meta Ads, Search Console, GitHub and RSS) are not in this build; any MCP server can be connected from the catalogue.
+
NeuralVault Business
Everything above, unchanged
Business metricsRevenue, ad performance and channel stats pulled onto one timeline that updates itself.In developmentThe page ships and every figure currently reads empty.
CanvasThe .canvas files in your vault, open beside the work.In developmentRead-only in this build. The app can open and read a canvas and cannot yet edit one.
CalendarEvents the agents can read, so scheduled work knows what your week looks like.In developmentRead-only in this build. Events can be read and not yet added from the app.
A sync serverPer-user accounts and folder-scoped permissions, so each person sees their own work and no more than that.In developmentThe app can connect to a sync server and sync, and each person signs in with their own account. There is no settings screen for it yet, and accounts are created on the server itself, not from the app.
Role-scoped agentsFinance sees the accounting agent. Nobody sees more than their role allows.In development
Team commsWire brings channels and email alongside the work instead of in a separate tab, with anything outbound waiting for a person rather than sending itself.In developmentNot in this build. Wire is out of the app entirely until team channels have a backend.
A security reviewWhat the agents may reach, who may see what, and what leaves the building, checked before anything runs.In developmentThe in-app page lists failed sign-ins from the last day, accounts and their folders, and paired devices, and lets you revoke one. It needs a sync server and has no export or alerts. The wider review is still work we do with you.
Deployment and supportThe whole thing built onto dedicated hardware inside your organisation, and kept running.
More than one vault on one serverNamed vaults on the same deployment, so departments or clients stay separate without a second machine.In developmentPart of the sync server, which no shipping app command reaches yet.
Clear the queue from anywhereThe approvals queue reachable over HTTP, so a pending action can be dealt with from another device rather than only from the desk it started at.In developmentWaiting on the approvals queue itself, which is only partly built in this build.
Backups on an intervalThe vault snapshotted on a schedule, without anybody remembering to do it.In developmentThe scheduler runs interval backups. Choosing where they land is part of a deployment rather than a setting in the app.
So the question is not which product fits. It is whether you need that layer yet. If you do, go to NeuralVault Business. If you do not, nothing on this page is a compromise.
What It Costs
Pick a plan. The AI comes with it.
Every plan is NeuralVault Personal plus a usage balance for NeuralVault routing: choose a model from our list, the calls are paid from your balance, and there is no provider account to set up. Your own API keys and local models still work on every plan. The monthly plans start when the Stable version is released, in the next few weeks. During the Beta everyone has Personal.
Start here, free
NeuralVault Free
A working slice of what Personal does. The same application with the paid capabilities locked, so you can point it at your own material and see what a paid plan adds before you spend anything. A free account, no card, and nothing expires. This is a Beta, public early access. Expect bugs. Keep a backup of your vault.
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
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).
The install
It installs for your user account only, so Windows never asks you for an administrator password. About 119 MB to download.
On your own API key
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.
On a local model
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.
How you power it
Where does the model come from?
NeuralVault has no AI inside it, on any edition. Pick where the thinking happens.
Pick from 390+ models and the calls come out of your balance. Nothing to connect. NeuralVault lists only models that can use its tools. The usage balance opens soon.
Monthly plans
A plan for every way you work
From a first try to full-time coding. Every plan is software plus a usage balance in one price, so pick the amount that fits and top up if you need more.
Show prices in
You are billed in pounds sterling (GBP). The figure above is shown in your chosen currency so you can follow what you pay, and is approximate: the amount charged is the pound price.
NeuralVault routing: pick from 390+ models, nothing to connect
Every Personal capability, on your machines
Your own keys and local models still work alongside it
+
Run low? Top up any time. Top-up money is added to your balance on top of your monthly balance and is not reset each billing cycle.
Billed in pounds sterling. Shown in dollars, euros or pounds so you can follow what you pay; the dollar and euro figures are approximate and the amount charged is the pound price. Your monthly balance resets each cycle. Tax at checkout. The terms are the software licence.
Already have your own API keys, or run a model on your own hardware? Personal on its own is $20 a month (+ tax where it applies): the software licence and only that. The app contains no AI, and model usage is billed by your own provider.
Buying usage from us opens soon. These are the rules it counts by.
A real amount of money
Your balance is shown in your own currency, not in points to convert. It is never rounded up.
The price is the price
Each plan is one all-in total. Tax is added on top and shown as its own line at checkout.
Charged what the call cost
The provider reports the exact cost, converted at a published European Central Bank rate.
Always on screen
Your balance sits in the corner of the app, with a ring that fills as your balance goes.
Two balancesYour monthly balance is spent first and resets each billing cycle. Top-up money is separate and is not reset by a cycle.
Warns in words, not only colourIt says low, very low and almost out in words, so the warning does not depend on seeing a colour.
Your own spending limitIf you do not want to spend over a set amount, set a daily or monthly limit. If you would rather have none, switch the limit off and use as much of your balance as you like.
Never counted twiceEvery charge is one line in a record that is only added to, so a retried payment cannot bill twice.
On your own API key or a local model none of this applies: your provider bills you and your messages never reach us.
Machines
Install it on every machine you own. Devices are unlimited, so a new laptop or a reinstall never costs you a slot.
At the same time
Unlimited devices, and up to five copies can run at once, signed in at the same time. Start a sixth and you can end one right there, no need to be standing at it.
Sync
The same vault on every machine you own, without a server in the middle. In development: it is not in the build yet.
Free is the same application with the paid capabilities locked, so trying it costs nothing and moving up is a subscription rather than a reinstall. Running a company rather than a codebase? NeuralVault Business is priced to the size of the deployment and quoted after a free consultation. Weighing the three of them up? See all three editions side by side.
The Release List
The first build goes to this list.
A release list, not a newsletter. The only thing that is ever sent is news of a build: the first download when it is ready, and after that the releases and feature changes big enough to be worth your attention.
It is in active development and the interface is still moving. That is the reason to be early rather than a reason to wait: the people who get in first are the ones whose friction decides what ships.
The first build, the day it is downloadable
New releases and major feature changes after that
Never a patch note, and your address goes nowhere else
NeuralVault ReleasesOpen
The Release List
Be first to the build.The download lands in your inbox the day it is ready. After that you only hear from us when something genuinely changes what the app does. Never a patch note, and your address goes nowhere else.
Thanks. You are on the list. We will be in touch when the first build lands.
Takes about four seconds. No account, no card.
Welcome aboard.You would be joining while the edges are still rough, which is the point: what you find gets fixed first.
Stay In The Loop
Hear about it when it happens.
No spam, no drip sequence. Pick what you want to hear about and nothing else.
