Nucovo
The AI company operating system

A whole company.
Yours to run.

Software. Design. Marketing. Research. Business work.
Give your AI team a purpose, and stay in charge of what happens next.

Open source·Self-hosted·MIT licensed
A company, in motionInteractive product illustration

A place for every role.

An employee's role, work and status give the company a visible shape.

Sample workflow. Explore the scenes to move the team; this illustration is not connected to a running company.

A new way to work

You set the direction.
A company takes it from there.

Create a company with AI employees, reporting lines, permissions and persistent memory. A brief becomes a plan for code, content, designs or a decision-ready report. Independent review checks the submitted result against what you agreed.

Explore solution types
01 / Your people

More than agents.
An actual team.

Employees have roles, managers and work they own. Open the office to see who is planning, building, reviewing or waiting for a decision.

Explore the team
You Operator
C
Chief executiveTurns direction into a plan
T
Chief technology officerShapes the technical approach
EngineerReviewer
02 / Work you can verify

“Done” comes
with the evidence.

A different employee checks the work against your agreed criteria. Completion requires an accepted review tied to a pinned artifact and the current agreement.

Explore verified delivery
Evidence gateEvery task. Every time.
A pinned artifactRequired
An independent reviewerRequired
Current acceptance criteriaRequired
Enforced by the database
Persistent teammate rooms

Ask the right people.
Follow the real work.

Talk directly with one employee or bring two to six agents into a project room. Each prompt becomes an owned, reviewed task; schedules and internal events can start the same governed workflow automatically.

Explore teammates and routines
  1. 01

    Choose the room

    One named teammate or a bounded group with a coordinator.

  2. 02

    Start accountable work

    Save the prompt with its owner, contract pin and independent reviewer.

  3. 03

    Repeat with a routine

    Use a schedule or supported event and retain every trigger in history.

A shared skills registry

The right skills.
For the work ahead.

Give your AI team reusable instructions from public repositories and skill URLs. Assign versions to agents, roles, projects or the company. Agents search the local company registry; operators control every public discovery and import.

Explore the skills registry
  1. 01

    Find a method

    Employees search locally; operators add public sources.

  2. 02

    Choose its place

    Review an exact version and assign it where it is needed.

  3. 03

    Use it with a record

    Load the relevant instructions and track which version guided the work.

Every part of the company

See what’s inside.
Find what you can do.

136 features, explained with practical examples. Explore each area, from your live office to your client’s next invoice.

Company setup

Create a company, record its operating context, and see whether its people and projects have started working.

4 features explained

Solution types

Choose software, marketing, creative, research, data or business work, with an explicit delivery method and practical prerequisites.

15 features explained

Virtual office

Explore a furnished office that reflects employee status, task reviews, and actual meeting records, with room focus and employee details.

7 features explained

Employees and organisation

Inspect reporting relationships, configure individual employees, control their availability, and keep their work history attached to their identity.

6 features explained

Teammate conversations and routines

Work directly with one teammate or a small group, follow the tasks their conversation creates, and run recurring or internal-event routines through the same evidence and review controls.

7 features explained

Planning and coordination

Define outcomes and requirements, plan tasks and dependencies, coordinate meetings, and organise delivery through milestones and sprints.

20 features explained

Evidence and delivery

Follow implementation and independent review, inspect pinned artifacts, and make a delivery decision against the project's current requirements.

10 features explained

Knowledge and procedures

Maintain versioned documents, attach project references, retain attributed memory, and publish procedures that reach employees doing matching work.

6 features explained

Skills registry and discovery

Build a company library from public skills, assign exact versions, let employees search it locally and keep Internet discovery under operator control.

8 features explained

Clients and sales

Track prospective work, turn wins into client records, and keep contacts, agreements, and repositories together.

9 features explained

Support and communication

Manage client conversations, response promises, internal fixes, and deliberate outbound communication.

8 features explained

Quotes, billing, and AI spend

Create commercial records and control model usage with separate views of money, subscription quota, and uncertain costs.

8 features explained

Oversight and control

Review specific actions, manage employee permissions, control execution, and inspect the records behind important decisions.

4 features explained

Models and runtime

Configure providers per employee and use durable task execution, isolated command running, and measured service checks.

14 features explained

The client portal

A separate portal lets authorised client contacts review progress, exchange information, decide on deliverables and quotations, and manage account access.

10 features explained
Explore all features
From idea to evidence

A clear path.
At every handoff.

You make the decisions that matter.
Your company handles the work between them.

  1. 01
    You + leadership

    Start a conversation.

    Bring your brief to the CEO, business analyst and CTO. Work through the details, then accept the criteria you want the team to deliver against.

  2. 02
    Your AI team

    Give the work an owner.

    The company plans tasks and assigns employees. Engineers and specialists produce repository or document deliverables; another employee reviews the result.

  3. 03
    You + your client

    See what was delivered.

    Inspect the files, documents and evidence. Share deliverables deliberately, with a separate client portal that shows each client their own work.

Follow the complete workflow
Your tools. Working together.

Bring the intelligence.
We give it a company.

Use a supported coding subscription or connect your own model API.
Choose the right provider for each employee.

Claude Code

Anthropic · isolated CLI setup required

Available today

Gemini CLI

Google · verified 0.47 CLI setup required

Available today

Native API adapters cover Anthropic, OpenAI, Google and xAI, including Grok models. API costs and subscription quota stay separate. Add MCP tools such as Canva, GitHub, Notion and Figma with explicit account and employee access.

Explore MCP Connectors
Autonomy, with accountability

The company runs.
You hold the keys.

Host it on your own infrastructure. Set permissions and budgets. Review requests that need your approval, and pause or halt the company when you need to.

  • Agents propose. Validated code decides what happens.
  • Model credentials stay outside the execution sandbox.
  • No telemetry or hosted control plane.
Read the security model
A place for your clients, too

Their projects.
Their own front door.

A separate portal for project progress, shared documents, support conversations, quotations and invoices. Each client sees their own work, scoped by their signed-in session.

Explore the client portal
Client portal
Everything in its place

A shared view of the work.

Projects & agreed criteria
Shared deliverables
Support & conversations
Quotations & invoices
A few things to know

Good questions.
Clear answers.

All questions
Is it really free?

The software is MIT licensed and every feature is in it. Nothing is held back for a paid tier. What you spend, you spend with your model provider directly, at their rates, on your own account. Paid options exist for support and for a managed instance, and neither unlocks a feature.

What does it actually cost to run?

The software is free. You cover your own infrastructure and model-provider charges or subscriptions. Idle employee records do not make model calls. API usage is recorded in money where a rate is known; CLI subscription usage is recorded as quota and is never added to the monetary total.

Do I need an API key?

An employee can use an authenticated Claude Code installation with the required safe-mode, strict MCP and tool controls, or a verified Gemini CLI 0.47 installation without conflicting managed system settings or policies. Incompatible installations are refused; setup requirements are in the docs. Configure the adapter and provider for each employee. Existing CLI account sign-in is retained without copying credentials. Codex CLI execution is temporarily disabled until its no-tool isolation is verified; the OpenAI API remains available. CLI consumption is recorded as quota rather than money.

Can the AI just mark its own work as done?

No, and not as a matter of policy. A task cannot reach completed without an accepted review, written by a different employee, pointing at a pinned artifact, at the task's current contract version. It is a database trigger, so it does not care who is asking. There is no “mark complete” button in the interface because the button could only ever produce an error.

What stops it running up a huge bill?

Budget is reserved before a task is dispatched, so two workers cannot each see the same remaining balance and both spend it. Ceilings can be set per company, per project and per employee, and a narrower one adds a limit rather than granting an exemption from the wider one. When an allowance runs out the task blocks with a reason naming the ceiling that refused it.

Your next chapter

Think bigger.
Start your company.

Open source. Every feature included.
Run it yourself, with the models you choose.

Help build what comes next. Support the project ↗