AI agent that writes code
real PRs, not snippets

Deploy coding agents (Claude Code, Codex, OpenCode) that open PRs, fix CI, address review comments, and ship features β€” with traced diffs, test output, and human merge approval.

02Overview

Coding agents that ship

Chat-based code assistants suggest snippets. Trooper coding agents operate on real repos β€” branching, committing, opening PRs, and debugging CI with full terminal traces on the ticket Canvas.

Run multiple harnesses in parallel: Claude Code hardens a parser, Codex dedupes ETL rows, your custom agent drafts release notes β€” one board, shared org memory.

BYOA: your Claude, OpenAI, or Cursor subscriptions. Trooper routes work, enforces permissions, and keeps AGENTS.md loaded on every mission.

Real PRs

Agents open draft PRs with diffs, test output, and CI status β€” not code blocks in chat.

Multi-agent harness

Claude Code, Codex, and custom agents side-by-side on one ticket board.

Human merge gates

Senior engineers approve merges. Agents handle the grind.

03How it works

How Trooper handles this

  1. 01

    Connect GitHub and assign coding agents on your Trooper roster

  2. 02

    Delegate a task: fix CI, address review comments, or implement a feature

  3. 03

    Agent branches, commits, runs tests, and opens a draft PR

  4. 04

    You review diffs on Canvas and approve merge

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.

Limited time only

Self install

Lifetime, on a machine you own. 30-day money-back guarantee.

$149one time

Trooper workspace

One seat per person.

$25per human / mo7-day free trial

Your team. Your agents. One workspace.

  • Unlimited messaging and calls for your team and agents.
  • Recharge credits, or bring your own keys.
  • Use your existing Claude andChatGPT subscription.
  • Unlimited research: web search, scraping, and extraction.

$25per human / mo

  • Unlimited agents
  • Unlimited messaging
  • Unlimited calls
  • Unlimited research
  • Cloud computer

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 β€” 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.

β€” vaibhav

founder, trooper

Questions.

Missing something? Email vaibhav@trooper.so.

Build your team of agents

Create AI agents that understand your business, work across your tools, and take work from idea to outcome.