ayoo.ai

Desktop app · Local first

One chat box is one assistant.
This is a whole team.

Pick specialists, run each of them on whatever model you like — on your own hardware or hosted — and give them a shared memory of your work. Everything stays on your machine.

macOS · Windows · Linux — early access opening soon

55+
AI specialists, ready to use
15
pre-built teams
15+
model providers, local and hosted
4
modes, solo to organisation
1
database, on your machine

Why a team beats an assistant

A normal chat window gives you one voice, on one company's model, with no memory of your work.

Any model, anywhere

Run one role on a model on your own hardware, another on a hosted frontier model, and compare them side by side in the same conversation.

Specialists, not a generalist

A Security Expert, a QA Engineer, a Copywriter — each set up for its job, each on the model that suits it.

Teams, not one voice

Send a question to three roles and let them build on each other's answers, each one addressing the part it's best at.

Memory that persists

Your documents and past conversations stay searchable and get used automatically, instead of being re-explained every session.

Projects, not loose chats

Everything grouped by what you're working on, so three jobs at once never bleed into each other.

Your machine, not someone else's

Conversations, memory and API keys live in a database on your computer. Nothing is uploaded to run the app.

The model is a setting, not the app

Everywhere else you pick a model and that's the product. Here it's a choice you make per role, per task, per project.

On your hardware

Ollama and MLX, pointed at whatever you're running locally. No cost per request, nothing leaving the machine.

Hosted

OpenAI, Anthropic, Google — the frontier models, for the work that genuinely needs them.

Your own infrastructure

Azure, AWS Bedrock, vLLM, or any endpoint you can give a URL to, with custom auth headers where you need them.

Mix them freely

Put the cheap fast model on drafting and summarising. Put the expensive one on the architecture review. Keep anything sensitive on a model that never leaves your machine, while the rest of the team runs hosted. One conversation, several models, no juggling of tools or tabs.

Prove which one you actually need

The Prompt Analyzer runs the same prompt across several models side by side, with what each result cost.

What people find

Most of us over-buy on model size out of caution. Run the comparison against your real work and a much cheaper model usually handles the bulk of it — and you learn exactly which tasks are worth the expensive one.

Memory

One searchable place where everything you've given the app lives.

Drop in specs, contracts, policies, notes, reports, source code — whatever the work involves. It gets indexed and becomes background knowledge the AI actually draws on, rather than something you paste in again every time.

Your conversations are part of it too. Every session is kept and searchable, labelled with which role said what, so a decision made three weeks ago in a team discussion is still findable.

Memory comes in layers

An answer draws on everything the person is entitled to and nothing beyond it — a shared base for the group they belong to, the project they're in, and the session they're working in right now.

Base memory shared by a group

Standards, policies, reference material and house templates that everyone in the group works from.

Project memory this piece of work

The documents, specs and decisions belonging to one job — kept apart from every other job.

Session memory the conversation at hand

What you and the team have said so far, retained and searchable long after you close it.

Scoped where it should be

Memory is bound to projects and groups, so one client's material never turns up in an answer about another client's work.

It compounds

Every document added makes every role using it more useful — and in a shared base memory, it does that for everyone at once.

It grows with you

Four modes, each adding to the last. Start wherever you are and move up when the work asks for it — one person, a small team, or an organisation.

Simple First time out

A chat box, a model picker, light or dark. Everything else stays out of the way until you want it.

Business Teams and content work

The role library, pre-built teams, the template library, simple step-by-step workflows, and cost tracking so you can see what you are spending.

Developer Technical work

The visual workflow designer with branching, memory and document indexing, template authoring, MCP tooling, the Prompt Analyzer, and detailed logging when something misbehaves.

Enterprise Oversight and accountability

Audit logging, budget controls, a governance dashboard, compliance workflows, and executive roles — for work that has to be answerable to someone.

Groups, roles and governance

Not everyone should get the same setup — or see the same memory. Roles decide what a person can do; groups decide what they can draw on.

Share a base memory across a group

Create a group and give it a base memory: the standards, reference documents, policies and house templates everyone in that group works from. Anyone in the group draws on it automatically, from their first session. Update the base once and everybody's answers improve at the same time — nobody has to be told to go and re-read anything.

Groups can overlap. Someone on a spatial project can sit in both the GIS group and the delivery group, and get both bases without either one leaking to people outside it.

Capabilities follow the role

What a person opens into is determined by their role, not by what they happen to discover in the settings.

Which mode they land in

A first-time user gets a chat box. A developer gets the workflow designer, MCP tooling and logs. Nobody has to grow into an interface they did not ask for.

Which specialists appear

Technical roles and teams for engineering, analysis roles for data work, executive personas for oversight — the library filtered to what is relevant.

Which models they can reach

Approved endpoints only. Sensitive roles can be held to models running inside your own network, while others reach hosted providers.

Which memory they can see

Group membership sets the base. Legal material is not reachable from an engineering role, and a contractor sees the project they are on and nothing else.

What they are able to spend

Ceilings and alerts per role, so heavy analytical work gets the headroom it needs and routine work does not quietly run up a bill.

What gets recorded

Audit logging on the roles that need to be answerable, with the activity trail attached to the work rather than kept in a separate system.

The controls behind it

Audit trail

A record of activity — which models were used, on what, and when.

Budgets and alerts

Ceilings per role, team or provider, with warnings before the limit rather than after it.

Approved providers

The endpoint list is a decision, not a free-for-all. Users choose from what has been sanctioned.

Managed credentials

Keys stored encrypted and injected automatically. Nobody pastes one into a chat or commits one to a repo.

Environment separation

Dev, staging and production kept distinct, so testing can never touch a live configuration.

Policy dashboard

How the app is actually being used, measured against the rules you have set for it.

Why it matters at any size

At two people this is how you keep one client's documents out of another client's answers. At two hundred it's how you answer an auditor. Same mechanism either way.

Built for people whose work doesn't fit one model

You assemble the roles, models and memory that suit what you actually do.

Developers

Coding, review and architecture roles with your codebase in memory, and a local model carrying the volume.

Data scientists

Benchmark models against your real workload, then keep the analysis roles and datasets together in one project.

Spatial and GIS analysts

Schema documentation and standards in memory, on models you can run locally when the data cannot travel.

Consultants and small teams

A project per client, memory kept separate, and a cost view telling you what an engagement actually consumed.

Regulated organisations

Enterprise mode for audit and budgets, with sensitive work pinned to models inside your own network.

Everyone else

Business mode, a team of three, and a template library that turns your best prompt into your default one.

What it takes off your plate

Most of this is already happening, just spread across five tools and a folder of scripts.

Instead ofYou get
An LLM workbench for comparing models The same comparison, wired into the app you actually work in
A separate coding assistant Technical roles with your codebase already in memory
Prompt scripts scattered across notebooks and repos A versioned template library with usage tracking
Pasting the same documents into chat every week Memory that already has them
A subscription per person, per tool One app, your own keys, your own models
No idea what any of it costs Spend, tokens and response times per provider

The workbench comparison is the closest one, and the difference is simple: a workbench is somewhere you go to test models and then leave. Here the testing sits inside the app you already work in, so the model you settled on is the one your roles are already running on.

Get early access

ayoo.ai is in development. Join the waitlist and we'll let you know when builds go out — no drip campaign, no reselling your address.

macOS · Windows · Linux · Bring your own models