a backlog in.
PRs out.
One agent in a terminal is a demo. Point several at real work and you need three answers: who decides what gets built, where parallel work happens without collisions, and what stops a plausible-but-wrong change from shipping.
$ brew install partyline-sh/tap/partylinewatch the line from the web
saved payment methods
requirements · 3 answered
delete a saved card
checkout-web
rate-limit the webhook
payments-api
save a card (SetupIntent)
claude · macbook
list cards at checkout
codex · build-box
migrate JWT refresh
token ceiling hit
cart race on double-submit
tests ✓ · review ✓
orphaned Stripe customer
reviewer: no revocation
webhook retry ceiling
PR #214 · squashed
how it works
plan
The Planning agent turns what you want into bounded, independently buildable tasks. You approve them to the backlog.
build
Workers claim tasks atomically — no two grab the same one — and build each in its own worktree off a fresh main.
ship
Every change runs your tests and an independent reviewer. Both pass → PR. Either fails → quarantined, never silently dropped.
what you're wondering
where does it run?
On your machines, in your git, with your keys. The web is the control room; the metal is yours.
which agents?
Claude Code, Codex, Gemini today — plus open-weight models through the llm bridge. Bring the one you already trust.
do I need the whole pipeline?
No. Plan without building, run a single task, or just use the session manager. It composes.
stop babysitting sessions.
review PRs instead.
$ brew install partyline-sh/tap/partylinefront half: describe to plan · back half: trust gates