NewTrooper for Mac — run your AI workforceDownload
trooper
[01]Unit brief

Trooper for Coding
Use Codex & Claude Code together.

Delegate to Claude Code, Codex, Cursor, and your own agents from one Trooper harness. Your subscriptions, your repos, one unified task board with traced diffs and PR workflows.

Deploy unitTalk to founder

Multi-agent coding ops

Trooper does not resell model access. You bring Claude, OpenAI, or any provider subscription — we bring the harness: routing, permissions, logs, and shared memory across every agent on your roster.

Claude Code and Codex open as real CLI sessions on one ticket. When the job needs a live page or a real machine, browser on demand and desktop on demand attach to the same mission.

Every edit, test run, commit, and PR open is traced in the ticket thread. Senior engineers approve merges; agents handle the grind.

Multi-agent harness

Run Claude Code, Codex, and custom agents as full CLI sessions on one ticket — live tool traces, not vague status dots.

Browser & desktop on demand

Spin up a live browser for PRs and CI, or wake an enrolled Mac when the work needs a real machine — same ticket.

BYOA subscriptions

Your API keys and IDE subscriptions stay yours. Trooper routes work, enforces permissions, and keeps shared org memory.

Tickets, PRs, and deploys across five tools, is how velocity dies.

Issue trackers, CI, code review bots, docs, and on-call stacks quietly pass 619/mo — while humans still write the glue scripts.

Issue tracker
sign in
$80/mo
CI minutes overage
sign in
$60/mo
Code review bot
sign in
$49/mo
Feature flag tool
sign in
$79/mo
Error monitoring
sign in
$99/mo
Docs wiki
sign in
$45/mo
On-call / Pager
sign in
$29/mo
API mock / catalog
sign in
$39/mo
Security scanner
sign in
$89/mo
Project board seats
sign in
$50/mo
+ Context switching PRs
+ Tribal runbooks Slack
+ Eng as glue all week
$619/mo10 logins15+ hrs*engineers are the integration layer
One Mission Control replaces all of it
Mission ControlCoding unit · online

ok Trooper, pick up this ticket and open a PR. go.

On it. Watch me work 👇

Reproduced the bug

Failing test captured with logs

Failing testRoot cause note
Opened the PR

Diff + checklist ready for review

PR #4821CI green
Updated the ticket

Status, links, and owners synced

Watching CI

Waiting on the last integration check

Ticket moving. Next bug won’t wait for a standup assignment. Review board

ok you're officially hired. run this every week forever 🫡

Trooper replaces the stackfrom $25/mo
Message Mission Control…

Build agents that run your playbooks.

Reusable coding runbooks — PR review, hotfix, and release train — traced on the board with GitHub, Slack, and harness agents.

GitHub webhook
Trigger
PR opened
Review harness
Inline comments
Notify #eng-prs
Merge gate
A/B test: comment style+18% approval rate

What this team doeson Trooper.

Each row is one clear capability — ask in chat, watch it run, approve before anything ships.

Your coding agents, one shared harness.

Bring Claude Code, Codex, and OpenCode onto the same ticket as real CLI sessions. They work in parallel with live tool traces — you keep the keys and the merge decision.

Coding — Multi-agent
ENG · parser hotfixIn progress

Fix invoice parser null rows

github.comacme-billing
Claude Codeworking
~/acme-billing · fix/parser-null-rows · tests/parser.test.ts
$ claude — resume session
Session attached · ACP harness
write_file tests/parser.test.ts — empty CSV regression
exec vitest tests/parser.test.ts▌
Codexworking
~/acme-billing · fix/parser-null-rows · src/parser.ts +5 −1
$ codex — acp
exec npm test — repro null-row failure
apply_patch src/parser.ts — filter empty CSV rows
exec npm run test:integration▌
OpenCodeready
~/acme-billing · fix/etl-dedupe · etl/dedupe.ts +3 −0
$ opencode — acp
apply_patch etl/dedupe.ts — ignore empty row ids
exec dedupe.integration.test
One ticket · three coding CLIsLive ACP

Repo rules that stick across agents.

Branch strategy, lint rules, and who reviews what load automatically. Every coding agent starts with the same standards — no re-explaining the codebase each time.

Coding — Memory
Org context for every CLIInjected
AGENTS.md
acme-billing

# Engineering agents

## Branch rules

- Default branch: main — no direct pushes

- Feature branches: fix/* or feat/*

- One agent checkout per branch

## Review & merge

- Parser owners review src/parser* first

- CI must be green before merge

- 1 human approval required

## Tests

- Unit + integration required on parser/ETL changes

- Lint: no console in src/; TS strict

Loaded for Claude · Codex · OpenCodeAlways on

Diffs, tests, and the PR together before merge.

See what changed, whether tests passed, and the PR write-up side by side. Approve merges from one view instead of hopping between GitHub tabs.

Coding — Review
Pull request #418Ready for review

fix(parser): skip empty invoice rows

parser.ts
src
+5−1
@@ -84,7 +84,11 @@ export function parseInvoiceRows(raw: string) {
8484 const rows = raw.split("\n");
85− return rows.map(parseRow);
85+ return rows
86+ .map((line) => line.trim())
87+ .filter((line) => line.length > 0)
88+ .map(parseRow);
8689 }
✓CI · 13 tests passedetl/dedupe.ts +3
Codex patch · Claude Code testsStaff merges

Browser and desktop, on demand.

Agents do not stop at chat. Spin up a live browser to check CI and PRs, or wake an enrolled Mac when the work needs a real machine — same ticket, same harness.

Coding — Runtimes
Runtimes on this ticketAttached

Browser on demand · Desktop on demand

Browser on demandSession live
Claimed
github.com/acme/billing/actions

Actions · acme/billing

integrationpassing

fix/parser-null-rows · 4.2s

lintpassing
✓ browser_navigate pull/418
✓ browser_snapshot CI green
browser_click Merge when approved▌
Desktop on demand
Studio-Mac
Terminal — ~/acme-billing

$ trooper device exec studio-mac

✓ git checkout fix/parser-null-rows

✓ npm run test:integration

13 passed · 4.2s

Seat held for review ▌

Same ticket · live browser · enrolled MacOn demand

How Trooper runs your code unit

From invoice parsers to release notes — agents execute full workflows, not single prompts.

Parallel patch missions

Three agents, three files, three test suites — all tracked with timestamps, tool calls, and pass/fail status.

PR workflow with review gates

Agents open PRs and post drafts for review. You authorize merges; nothing ships without command approval.

Shared codebase memory

Branch strategy, lint rules, and reviewer preferences persist across agents and sessions.

GitHub-native execution

Real commits, real branches, real CI — connected through OpenClaw skills and your private runtime.

Your troopers work for you.
Just you.

No action without approval

Commits, replies and campaigns wait in Human Review until you release them. Autonomy is a privilege you grant, not a default.

Your keys stay yours

API keys are never stored on our servers. Every organization gets an isolated workspace with encrypted connections.

Run it on your own hardware

Self-host the whole workforce, or point it at local models. Enterprise adds SSO, private VPC and on-prem deployment.

You are the board

Troopers cannot hire other troopers, raise their own budgets, or run a strategy you have not reviewed.

At any timePause.Resume.Override.Reassign.Terminate.

Simple pricing, by deployment.Pay for the plan you need.

Every plan runs on a private server with your keys. No surprise bills on model usage — you pay providers directly.

Self-installFree

Local Install

$0free forever

1 workspace · no connected devices · free forever on your machine

Free local install. Bring your own API keys; model usage is billed by your providers.

Team members

1 included

1

Workspaces

1 included

1
Download apps
  • Unlimited agents and chats
  • Adaptive memory and shared workflows
  • Skills, integrations, and browser automation
  • Install on Mac or Windows
  • Bring your own API keys
Lifetime dealLifetime

Solo Cloud

$149one-time

1 workspace · 2 team members · no connected devices

Bring your own API keys. Model usage billed by your providers.

Team members

2 included

2

Workspaces

1 included

1
Get lifetime deal
  • Unlimited agents and chats
  • Adaptive memory and shared workflows
  • Skills, integrations, and browser automation
  • Always-on managed cloud computer
  • Lifetime hosted access — pay once
Hosted by usMost popular

Trooper Cloud

$25/ month

2 team members included

Each workspace uses the selected tier ($25/mo). Additional members are $10/month.

Team members

2 included

2

Workspaces

1 included

1
Choose · $25/month
  • Unlimited agents and chats
  • Adaptive memory and shared workflows
  • Skills, integrations, and browser automation
  • Multi-workspace support and unlimited connected devices
  • Admin controls and team collaboration
Private deploymentCustom

Enterprise

Custom

Volume pricing and dedicated support

Self-hosted deployment with migration and custom agreements.

Team members

200 included

2

Workspaces

100 included

1
Talk to sales
  • Unlimited agents and chats
  • Adaptive memory and shared workflows
  • Skills, integrations, and browser automation
  • Private VPC or on-prem deployment
  • SSO, custom domains, and agreements
  • Priority support with SLA
See full rate card and FAQ

the dream.

notes

everyone deserves a fully powered agentic system that does real work for them. that power should not sit only in the hands of big corporations — so we built trooper for you, and made it free for anyone to use. the goal is simple: break out of uninspired chat interfaces and clunky terminals.

— vaibhav

@absurdfounder

Intel brief.

Missing intel? Transmit your question to vaibhav@trooper.so.

Try Trooper now.

Stand up AI units that write code, manage tasks, and connect to 3,000+ tools — without the overhead of hiring.

Get StartedDownload Mac App