ArimaOps
Free and open source · self-hosted

Build an AI team for any job.
Run it from your phone.

ArimaOps runs a team of AI agents for every project on your machine. A lead plans the work and hands out tasks, workers build in their own containers, a reviewer and a second model check each other, and gates decide when a task is really done. You watch it, steer it and approve what matters from any screen.

Get started View on GitHub
npx arimaops@latest
8 team templates 11 kinds of gate Agents on your CLI subscriptions or API keys Everything runs on your machine

A dev team planning, building and shipping reviewed pull requests — live on one screen.

How it works

A team with roles, a flow with gates

Every project starts from a template: its roles, the stages a task moves through, the gates between them, a starter board and its tool rules. Change any of it per project.

Specyou approve the spec
›
Plantasks cover every item
›
Buildtests and green CI
›
Reviewreviewer, second opinion, screenshots
›
Mergeyou merge the PR

Home is the team, live

Each agent orbits a core that reacts to the work. Cards show what it's doing, the task and stage it's on, and the tokens and cost it spent today. The strip below shows how many tasks sit in each stage and who's working them.

  • One lead, on-demand workers: only the lead stays on; workers start per task.
  • Agents talk through HQ: no agent can reach another's container.
  • Anything that needs you lands in one Inbox.
An agent's panel over Home: its live terminal, session, task and usage tabs.

Command center for every agent at once

Every agent of every project in one roster, needs-you first. Pick one to watch its terminal live, see its tokens and cost, and stop it or pop it out to another monitor. What's waiting on you and what just happened sit beside it.

The Command center: an agent roster with token meters, a live terminal for the selected agent, and Needs you and Activity panels.

The flow is yours to edit

Stages, the roles that work them and the gates between them, on a canvas. Add a stage, require a reviewer from a given role, a second opinion from another maker's model, screenshots of the running app for UI changes, or your own approval. HQ checks the change before it saves.

The Flow canvas: five stages with their roles and gates, and an editor for the selected stage.

Know what it costs

Tokens and estimated cost per agent, per task and per day, from each CLI's own logs. Spend caps per project alert at 80% and pause the workers at 100%.

The Usage page: team tokens today, estimated cost, the busiest agent, and a per-agent leaderboard with sparklines.

A board that moves on its own

The lead plans tasks with the files each one touches and a clear done-when. Columns show how long their oldest task has waited, and you can group the board by agent.

The Board: To do, Doing, Review and Done columns with task cards and their owners.
Templates

Teams for software, security, research and marketing

Dev

Ship pull requests

Spec you approve, tasks that cover it, one branch and one PR each with tests and green CI, a reviewer, a second opinion on high-stakes work, screenshots for UI changes.

Security · Red

Engagements in scope

Scope first, then recon, threat model, exploitation and a scored report checked by a second model. Out-of-scope targets are refused.

Security · Purple

Attack, then defend

Red's engagement plus a defender that maps each finding to ATT&CK and D3FEND and writes the detection that catches it.

Security · Blue

Incident response

Detect and analyse, contain only with your approval, eradicate and recover, then lessons learned. A plan before every change.

Research

Every claim cited

Sources logged first, claims that cite them, a fact-check by a different model and a report signed off by a third.

Marketing · Sales

Drafts only, enforced

Copy and outreach drafted against a brief and checked by an editor from another maker. Nothing is sent: you approve and send.

Any screen

Steer it from your phone

The same HUD on a phone or tablet, sized for touch. Approve a spec, answer an agent, read a terminal or stop a run from anywhere you can reach your HQ, with an authenticator code for anything risky.

Safe by default

Agents work in their own container or sandbox; outbound traffic goes through an allowlist. Keys are encrypted and reach only the agent that uses them.

You stay in charge

Owner, operator and viewer sign-ins. HQ never merges for you, never types your secrets, and never answers a CLI's trust prompt without you.

ArimaOps on a phone: the team in orbit and the flow's stages above the tab bar.
Case study

One brief in, six reviewed pull requests out

A Dev team built Pipewell, a small data pipeline on open weather data, from a one-page brief. The reviewer ran every branch and sent back three real bugs before anything merged; a verifier ran the finished pipeline from a fresh clone.

6pull requests merged
47tests, all passing
3bugs caught in review
~$7.41estimated model cost
Read the case study →
Get started

Running in a few minutes

1 · Start HQ

From inside a git repo:

npx arimaops@latest

Or run HQ and its memory database with Docker Compose.

2 · Pick a team

Name the project and choose a template. The setup checklist shows anything missing on your machine, with the exact command to fix it.

3 · Brief the lead

Press Start team and tell the lead what to build. Approve the spec, then watch the board move.

Try the demo first

No HQ, no accounts: sample projects with agents working through their flows, in your browser.

git clone https://github.com/sachindots/arimaops
cd arimaops
pnpm install
pnpm dev

What you need

  • Node.js 22+ and git
  • tmux on macOS and Linux, so agents outlive HQ
  • Docker for Container mode (recommended), or Docker Sandboxes
  • An agent CLI you're signed in to, or an API key
  • GitHub CLI for pull requests and reviews

Free and open source: the core is MIT and AGPL-3.0. Licence · Getting started guide