Orbi AI Agent

English | 简体中文

Orbi

Label a GitHub Issue. Get back a reviewed, merged PR. Release when you decide.

Try Orbi Cloud — 3 merged deliveries free · no server, no credit card required

See one real loop: Issue #1367 → PR #1370 → Release v0.5.47

Orbi is an open-source software dark factory: a software delivery system for GitHub. You define the goal and acceptance criteria in an Issue and label it ai-ready; Orbi implements it in an isolated worktree, runs tests, opens a PR, and takes it through independent review, fixes, and merge. When you request a release, Orbi runs the release gates and publishes the tag and release notes. GitHub Issues are the only state store—no database, queue, or daemon.

Ledger: merged PRs · closed Issues · tagged releases — the repository is the record.

Website orbi.build ｜ Documentation https://docs.orbi.build/ ｜ Discussions ｜ Docker GHCR · Docker Hub

Prefer to run it yourself? Follow the Quick start below. Cloud founding members get 50% off forever with the code FOUNDING50 at checkout (6 places).

Quick start

git clone https://github.com/orbi-build/orbi.git && cd orbi
uv tool install --force --reinstall --editable --python python3 .  # compatible system Python (>= 3.14, e.g. Fedora 43 / current Arch); older (e.g. Ubuntu 24.04's 3.12): --python 3.14 so uv provisions it

Want just the CLI? It's on PyPI as orbi-cli (requires Python ≥ 3.14; the command stays orbi): uv tool install orbi-cli (older system Python: add --python 3.14 so uv provisions one) or pip install orbi-cli in a Python ≥ 3.14 environment; verify with orbi --version → orbi <version>, uninstall with uv tool uninstall orbi-cli. To run Orbi itself, use the one-line installer at the top of Getting started — it creates the editable install Orbi's deployment drives.

Ready check (before setup)

• uv: uv --version; Pi and its provider: pi --version, then pi --print "reply with the single word: ok"
• GitHub CLI ≥ 2.94 (official repository — Ubuntu 24.04's package 2.45.0 is too old): run gh auth login once, then verify gh auth status
• Linux — systemd user session: systemctl --user status
• macOS — launchd GUI session: launchctl print gui/$(id -u) (not yet verified on real hardware; reports welcome)

Choose the mode in Getting started: bootstrap uses this checkout as repo_dir; External single-repo mode uses it as deploy_home and a foreign repository as repo_dir.

cp src/orbi/example_config.toml orbi.toml
# edit orbi.toml: set source_repos = ["OWNER/REPO"] (the repository whose Issues Orbi delivers)
orbi setup --config orbi.toml  # 4. run one-time setup (checks prior gh auth, labels, scheduler units (systemd/launchd), and checkout; idempotent)
PYTHONPATH=src python3 -m orbi.runner --config orbi.toml  # 5. manually run one tick (for initial verification; the timer schedules normal runs)
orbi doctor --config orbi.toml  # 6. verify deployment health

The loop, in 35 seconds

Another real delivery, recorded from the live GitHub pages — including the review that rejected the first attempt:

<video src="https://github.com/user-attachments/assets/1f0d3a62-5fc9-44ae-bf68-b312a6a55f85" controls muted></video>

1. An issue — a bug, labelled ai-ready
2. It writes the code — PR #1023, on a recorded base SHA
3. The review says no — one Major finding, naming src/orbi/release.py:2377 and the fix
4. It fixes itself — more commits, until the checks go green
5. It merges — 9 commits, +427/−43, only after the review passed
6. A tagged release — v0.5.17, with the Issue and PR in the notes

Why Orbi

• GitHub Issues are the task pool: the ai-ready label dispatches work, and the delivery record (comments, PRs, and CI) is complete by default, with no second task system;
• Fully automated: a user scheduler timer (systemd on Linux, launchd on macOS) triggers a tick every 5 minutes. Normal operation needs no status command, polling, or supervision;
• Independent review + merge gates: after a PR opens, an independent review session reviews it and fixes findings in the same session. Reviewed code is what merges, and only with CI green on the latest base: if the base moved after the review, the Runner merges it into the delivery itself when there is no conflict and waits for CI on the new head before merging; conflicts or an outside push go back to review. AI never merges or pushes protected branches;
• Fail fast: command errors fail immediately and leave the evidence in the logs. The Issue is marked ai-blocked for a human decision, with no silent fallback;
• Observable end to end: every journal log and GitHub progress comment carries the same run_id, so the complete timeline can be reconstructed with one grep.

What it does

GitHub Issue (ai-ready)
  → Claim: create a feature branch + isolated worktree (from the frozen origin/main SHA)
  → Pi development: plan → implement → test → verify
  → Commit delivery (the Agent stops at the commit)
  → Runner closeout: sync the latest base, push, and create a PR (body includes Fixes #N)
  → Independent review (fixes in the same session) → merge gate → merge

• Each task gets its own run: the branch, worktree, logs, and PR are all associated with the same run_id; retries create a new run and preserve the old evidence unchanged;
• Failures are classified clearly: recoverable failures return to the same PR for continued fixes, while unrecoverable failures mark the Issue ai-blocked for a human;
• Supports orbi add for dispatching work, status for viewing the queue, session for following the Pi session, install-units for idempotently installing the scheduler units (systemd on Linux, launchd on macOS), and doctor for read-only diagnostics.

Documentation

Topic	Entry point
Documentation home	https://docs.orbi.build/
Getting started (prerequisites, configuration, first run, smoke test)	Getting started
One-time setup (labels, units, transport migration)	One-time setup
Workflow (state chain, labels, P0, Epic, Release)	Workflow
Operations (timer, journal, unit drift, recovery)	Operations
Public contracts (interface inventory, status and progress formats)	Public contracts
Testing, coverage gates, and remote CI	Testing
Contributing (Issue granularity, KISS/LEAN, PR flow)	Contributing
Chinese documentation	docs/zh/

Development and contribution

See the development contract in AGENTS.md, and Contributing for dispatching Issues, reporting bugs, and submitting PRs. Runtime code lives in the src/orbi/ package (Issue #168 src layout; the editable finder maps the whole package, so new modules need no reinstall). The checkout root has no orbi.py (it would shadow the installed package); the compatibility entry point is python3 -m orbi.cli, not the formal usage path.

License

Orbi is open source under the GNU AGPL-3.0, with the Sustainable Use License (v1.0) as an alternative. Pick either license.

In practice:

• Run Orbi on your own repositories for free forever—personal or internal company use, at any scale, under either license. Modify it, self-host it, run it across a thousand repositories; no authorization needed.
• You may share it—free of charge for non-commercial purposes under the SUL; under AGPL-3.0, offering a modified Orbi as a network service means publishing your changes.
• Commercial authorization is needed only to sell Orbi itself—hosting it as a service for customers or embedding it in a paid product (SUL); AGPL-3.0 has no such restriction.

Unsure which side your use falls on? Ask in Discussions.