Public alpha

Bring one real workflow, not a slide deck.

The public alpha is self-serve: install from PyPI and run it on your own repos today. The pilot track is for teams using agent tools across multiple repos, services or review paths — bring one concrete workflow, we run it through the protocol together and learn where the control plane helps or gets in the way.

PILOT INTAKE

Install the public alpha Discuss a team pilot

typed plan cross_plan.md

gate findings review_changes.json

run diff diff.patch

event spine events.jsonl

cost split metrics.json

handoff decision phase_handoff.json

01 Good fit

You have cross-system agent work today.

A good alpha workflow touches more than one repo, uses more than one worker or has a review/handoff step that is painful enough to name.

Your team is roughly 5–50 engineers shipping across more than one repo, service or review path.
You already use two or more agent tools day to day — and their work has to land as one delivery.
You can share a representative workflow under NDA.
You care about review, evidence or handoff more than novelty.
You can give direct feedback after a run.

02 Choose the path

Self-serve is open. The pilot is selective.

Anyone can install the public alpha. The pilot track is for validating the delivery protocol against a concrete team workflow, not for providing generic autocomplete or a finished hosted service.

03 Know the ceiling

Today it is a per-machine, single-operator control plane.

Orcho runs on one machine per operator: no central RBAC, tenant-wide audit, or team budget enforcement yet. The delivery record is the run directories on that machine. That is the honest scope of the alpha — and because every run is plain local files you own, nothing is trapped if you walk away.

Next step

Move from the claim to the operating surface.

Inspect the technical contract, watch the proof, or run Orcho on one task. The deeper layer is always one explicit step away.

Install the public alpha Discuss a team pilot