Niumate

Assign work the way you would to a colleague.

Niumate turns AI into named experts with defined roles. You tell them what needs doing, they get it done on real work machines and real projects, and then bring the result back for you to confirm.

Named, with a roleBuilt per role, each owning its own patch.
Works on your machinesReading project files and running tools happens there.
Confirmations come back to youPayment, signing and authorisation are never decided for you.
14-day full-featured trial 10 members / 10 machines No payment info required
Working Lin · finance
Web / Feishu · your own model account
You

Put together this week's project progress report, only for project A, don't change any files, output Markdown and list what needs confirmation.

Goal · scope · limits · expected output
L

Got it. Filed under “Weekly progress report”, split into 3 work items. On it.

  • Pull this week's project A records
  • Write up progress and risks
  • List what needs confirmation
L

Report is ready. Two things need your confirmation: budget basis, next week's priorities.

Awaiting confirmation

Three ways in

Web, Feishu, desktop client.

You mostly assign work from the web and Feishu; the desktop client is for people who contribute a work machine.

Everyone

Web

Assign work, follow progress, confirm results, manage the organisation. The left side shows your expert team and the list of items; pick someone and chat like it's IM.

  • Nothing to install, and progress is readable on a phone
Whoever provides a machine

Desktop client

Connect your own computer to the organisation so experts can work on it. macOS, Windows and Linux; Linux servers install as a background service with one line.

  • Install, sign in, pick the organisation — done

A request made in Feishu shows up in the web conversation and item list too — both sides see the same progress.

A typical run

Say it, get it arranged,let it run, confirm.

You only take part in the first and last step — the middle does not need watching.

01

You say what needs doing

Pick an expert on the web home page and start a conversation, or tell the organisation assistant in Feishu. Not sure who to ask? The team lead takes it.

02

It becomes a request and gets arranged

Once understood, it is filed into the right item and anything hands-on is split into work items. The timeline shows how many work items were created and who is on each.

03

It runs on a work machine

The expert works on the machine in the background — reading project files, running tools. Progress is visible live and you can open the details.

04

It asks when needed, you confirm at the end

If something is missing, the conversation prompts you. When the result looks right, confirm and the item moves on. Wrong direction? Stop it and restate what you want.

These are all the words the interface uses: what you ask for is a request, it gets filed into an item (a group of work around one goal), and the item is split into work items, each executed by one expert.

Where capabilities come from

A role template is a starting point, not a cage.

Start from an existing role template, then swap the model, the machine or the capabilities as needed. Two employees on the same role with different models is fine.

Can it connect

Credentials

Keys to external systems: databases, third-party API keys, granted per person. Built-in types not enough? Define your own.

What tools are at hand

External tools

Platform-provided connections (search, Feishu and more) plus your own MCP connections. Granted per person — a tool that was not ticked simply cannot be called.

Two come with every organisation

The team lead, and platform upkeep.

Fixed division of labour, neither crossing into the other. Display name, avatar, style, model and machine are all editable; the remit is not.

Built-in employee What it handles When to go to it
Team lead Understands your goal, splits responsibility, coordinates the others, then confirms and sums up a result you can verify. The default point of contact for everyday work. Not sure who to ask? This is the one.
Platform upkeep Looks after Niumate’s own configuration only: credentials, experts and role templates, skills, work machines, run records. To inspect config, dig into run records or maintain credentials and skills. It will not arrange business work, change code or deploy.

Rather not click through settings one field at a time? Message platform upkeep from the home page. It reads the current config, explains the blast radius, and checks with you before anything sizeable — high-risk operations always come back to you first.

Onboard a new employee“Create a QA engineer called Ce, on model XX, working on this machine, with the database credential”
Capture a team skill“Turn our release process into a skill and give it to every engineer”
Define a credential type“Add a credential type for our internal CRM with endpoint and token fields”

Boundaries

What it will not decide for you.

Three hard rules are written into the built-in employees' remit. They are not switches you can turn off.

01

Human decisions come back to you

Anything involving payment, signing or authorisation is handed back. It is never decided on your behalf.

02

Project files and commands stay on your machine

Reading files and running tools happen on the work machines you approved. Code repositories stay where they are.

03

Credentials are granted per person, never shown back

Sensitive credentials go only to the employees that need them, and once stored the plaintext is never readable in the interface again.

Your boundary Work machines, project files and model accounts all stay on your side.
Work machineA real computer running the client · reading files and running tools happen there
Bring your own model accountThe key you obtained from the provider · model bills go straight to them
ProjectsRegistered project directories · imported Git repositories
CredentialsKeys to external systems · contents never shown back

FAQ

Worth settling before you try it.

Finer operational questions all live in the user guide, available once you sign in.

How are model costs handled?

Bring your own model account (BYOK) and pay the model provider directly — Niumate does not resell model usage. Common providers are supported, as are models on your internal network.

Where do code and data live?

On your own work machines. Reading project files and running tools happen on the machine running the client, and code repositories stay where they are. For a stricter boundary, talk to us about private deployment.

Can non-technical colleagues actually use it?

Yes. Assigning work means saying a sentence on the web or in Feishu — no configuration involved. Model accounts and work machines are set up once by an admin, after which members only ever see a conversation.

What are the trial limits?

Nothing is feature-limited during the 14-day trial: 10 members, 10 machines and the complete assign-and-confirm flow, with no payment info required. Model accounts are still your own.

Niumate

Sign up and get 14 days, fully featured.

14 days, fully featured 10 members / 10 machines No payment info required