Practical overview
When it fits
Use Orbi when the task starts as a clearly scoped GitHub Issue and the desired path is automated implementation, independent review, merging and release tagging.
Who it is for
- Teams managing scoped coding tasks through GitHub Issues.
- Repository maintainers seeking isolated implementation work and review-gated merging.
- Teams building a GitHub-centered continuous delivery workflow.
Documented uses
- Dispatch a labeled GitHub Issue to an autonomous coding run.
- Implement changes in an isolated worktree and open a pull request.
- Review a pull request against issue acceptance criteria.
- Merge the reviewed commit and create a tagged release.
- Trace runs through shared GitHub and journal evidence.
Requirements & limits
The project is open-source under AGPL-3.0.
- The workflow is centered on GitHub Issues labeled
ai-ready. - Review is tied to the issue’s acceptance criteria and only the reviewed head can merge.
- GitHub Issues serve as the state store rather than a separate database, queue or daemon.
- The documented scheduler path uses systemd on Linux and launchd on macOS.
- Failures can mark an issue
ai-blockedfor human decision, while run evidence is retained.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Set up Orbi for a GitHub repository
Prepare a documented Orbi deployment and perform its initial verification run.
Before you start
- A compatible Python environment; the README specifies Python 3.14 or newer.
- uv, Pi and its provider, and GitHub CLI 2.94 or newer.
- GitHub authentication completed with
gh auth login. - Linux with a systemd user session or macOS with a launchd GUI session.
Steps
Clone the Orbi repository and install it with the documented the command below command.
uv tool install --editableCopy
src/orbi/example_config.tomltoorbi.toml.Run
orbi setup --config orbi.tomlto check authentication, labels, scheduler units and the checkout.Run one manual tick with
PYTHONPATH=src python3 -m orbi.runner --config orbi.toml, then runorbi doctor --config orbi.toml.
Expected outcome
The deployment is configured, an initial runner tick has been attempted, and deployment health has been checked.
Guide limitations
- The documented macOS launchd check reports welcome but is not yet verified on real hardware.
- This recipe covers setup and initial verification, not a complete issue-to-release execution.
- The supplied workflow is documented for GitHub Issues and pull requests; other issue trackers are not covered.
Compare options for AI coding assistance
These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.
| Project | Documented purpose | Platform | Access and requirements |
|---|---|---|---|
| Orbi | Dispatch a labeled GitHub Issue to an autonomous coding run. | Cloud, Self-hosted, Server | The project is open-source under AGPL-3.0. |
| Llmcode | Inspect a project's directory structure with `/tree`. | CLI | The documented setup requires an API key and supports an API base URL and model setting. The project is open source under Apache-2.0. |
| Klaat Code | Open a project directory for terminal-based coding assistance. | CLI, Server | The README provides a global npm installation command and documents browser sign-in with a KlaatAI account. It also identifies the repository as open source under Apache 2.0. |
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 30 September 2026
- Original website title
- orbi-build/orbi · Official homepage title · retained in its source language