Wake up to pull requests.
Each Night, Yellowhammer picks the next Feature from your spec and runs your own agent CLIs on it.
The app




What it never does
It never writes a line of code itself, and it never merges to main.
The agent CLIs write the code. Yellowhammer judges between them: it routes each Work Card, runs the checks, and verifies the result against your specification.
No code of its own
Your agent CLIs write every line. Yellowhammer composes their instructions and reads their results.
No merge to main
It hands off at the pull request, one per repository. The merge is yours.
No cloud execution
Your code, credentials and models stay on your Mac. The Night runs on your existing subscriptions.
What you need
It sits on top of the tools you already use
Yellowhammer replaces none of them. You need a Mac on macOS 26 that stays awake through the Night, the Orca ADE, a Linear workspace, GitHub, and at least one supported agent CLI.
Worktrees
Orca ADE
Creates, places and cleans up a Worktree for each Feature and repository. Yellowhammer only holds its id and path.
The board
Linear
Intent comes from your Linear board, and every report goes back to it. In v1, the person running setup must be a workspace admin.
Pull requests
GitHub
Receives each Feature Branch and one pull request per repository. Yellowhammer writes to it and never merges.
Agent CLIs
The coding agents you already use in the terminal. They write the code. Each Work Card runs on a route: one agent CLI, one model and one effort level.
Claude Code
claudeProbed for unattended runs.
Codex
codexProbed for unattended runs.
Adding another agent CLI takes an adapter and a probe, not a configuration edit.
How it works
One Night, in three Acts
A Night is one overnight run for one Project. It runs in three Acts, author, build and land, each started on a schedule by macOS. You read the result in the morning.
author
It picks the work
It selects one Feature from your specification and works out which repositories it touches. It writes the Work Cards, each with a Definition of Done written before any code exists. It does this even when the board is empty.
build
Your agents write the code
Each Work Card goes to an agent CLI and runs in a Worktree, one Repo Lane per repository. The engine runs each repository's check itself. A failed try goes to a different model, then stops at limits you set.
land
One pull request per repository
It pushes each Feature Branch and opens one pull request per repository. A different agent verifies the Feature clause by clause against its Definition of Done. The merge stays yours.
Night Summary
You read the verdict
The Night Summary on your board says what landed, what is blocked and what needs you. A Work Card that needs an answer goes to Waiting on You, and you answer it in Linear.