Player profile
Orbi
A self-hosted issue-to-release runner: label a GitHub Issue ai-ready, and one agent session implements it on a branch while a separate review session checks the pull request against the Issue's acceptance criteria before the reviewed head is merged and tagged.
Profile
Where it fits
Orbi is an AGPL-3.0 Python runner that polls a repository for Issues labeled ai-ready, works each one in an isolated git worktree, and opens a pull request. Ordering between Issues comes from GitHub's native blockedBy links and milestones, so the queue lives in the repository rather than in a separate board.
It belongs in Parallel Coding-Agent Runners because it routes issues to agents and splits delivery across roles: an implementation session writes the change, an independent review session checks the diff against the acceptance criteria written in the Issue and sends it back for fixes, and the runner merges only the reviewed head before cutting a tagged release. It runs on the Pi agent engine with any OpenAI-compatible API or a Codex subscription; a hosted version, Orbi Cloud, runs the same loop.
Builder web analytics
Measure projects built with Orbi
Orbi closes the loop from Issue to tagged release; it does not observe what a release did to the product. Agent Analytics can supply that signal when the shipped surface is separately instrumented.
Orbi has no Agent Analytics integration. Instrument the deployed product separately and give whichever agent queries it its own Agent Analytics access.
First loop to measure
- a maintainer files an ai-ready Issue with acceptance criteria
- Orbi implements it, the review session approves it, and the reviewed head is merged and released
- the deployed surface, separately instrumented, reports page views and configured product events to Agent Analytics
- the maintainer or an agent reads those results and files the next Issue with the measured outcome as its starting point
Copyable prompt
Use Agent Analytics for this project. If event reporting is missing, add the tracker and report events for this project surface, including Orbi-released change, traffic source, signup, activation event, or funnel step. Verify events are arriving. Then fetch the last 7 days and compare them with the prior 7 days. Tell me which Orbi-released change, traffic source, signup, activation event, or funnel step moved users toward value, where users dropped off, which sources mattered, and what my agent workflow should improve next.