mmetwally-dev/project-autopilot

Give it a request. It plans, codes, reviews and tests the work with your coding agents, until it passes.
Install and set up a project in about a minute (Enter takes the default answers). Then run ap run "your request" .
A real 14-minute run, sped up. Left: ap run ; right: the live watch report.
Project Autopilot (ap) runs a team of AI coding agents on your repository.
You write what you want in one sentence. Autopilot gives each step to a
different agent and checks every result before it moves on:
text
Planning → Plan Review → Implementation → Code Review → Gate (your tests) → Verification → Final Review → you commit
A planner reads the related code and writes a spec (numbered requirements), then the plan and a task list.
A plan reviewer checks the spec, then the plan. The planner fixes them until the reviewer approves.
An implementer codes the tasks, one task per session.
A code reviewer checks each phase. The implementer fixes what it finds.
Your test suite (the gate) runs after each phase.
A verifier checks the phase against the plan and the test results.
A final review checks the whole change once at the end, including every requirement in the spec.
Each role can be a different CLI and model, for example Claude Code for
planning and review and a free opencode model for coding. The reviewers run
read-only, and Autopilot never commits or pushes: when the mission is done,
the changes wait in your working tree for you to review and commit.
Works with:
SpecKit — if your project uses
SpecKit (.specify/, specs//tasks.md), Autopilot picks up its tasks and
implements, reviews and tests them. Without SpecKit it writes its own plan
(SPEC.md + PLAN.md + TASKS.md) — nothing else to install.
Playwright — built in: the verifier checks
browser tasks in a real browser (install the browser once with
npm run playwright:install).
Agent CLIs — Claude Code, opencode, Codex and Antigravity, mixed freely
across the roles.
## Install
Needs Node.js 18+, Git and at least one signed-in agent CLI
(details).
bash
npm install -g project-autopilot
cd your-project && ap setup
ap run "your request"
ap is installed once per machine; each project is set up once with
ap setup (its own settings, slash commands and missions in .autopilot/).
If you forget, the first ap run in a project starts the setup by itself.
To update to a new version, run the same npm install -g command again; your
projects keep their settings. (Version 12 is the first public release; earlier
versions were private development.)
## Contents
Install
Choose how to use it
Get started
How a mission works
What runs where: support status
Commands
Slash commands in your agent
Adhoc reviews (plan-review, code-review, verify-file)
Mission control: stop, cancel, reset, rebase, finding
Watching a mission: the WATCH-REPORT
Roles, models and fallbacks
Limits: caps, retries and timeouts
Safety model
Platforms and runtime modes
Planning frameworks: standalone, SpecKit, GSD
Configuration
Files Autopilot creates
Troubleshooting and FAQ
Known limitations
Development and tests
Configuration reference
## Choose how to use it
| What you need | Run | Outcome |
| Build a feature or fix a bug from start to finish | ap run " " | A reviewed plan, coded and tested phase by phase, waiting in your working tree |