- Get Started

Quick Start Guide

Getting Started

OpenFlows is an autonomous AI software team that turns GitHub issues into reviewed, production-ready pull requests, running entirely inside your own self-hosted Coder environment. It stands up a small team of specialized agents that plan, write, test, and adversarially review code on your behalf. You stay in control of the important decisions; the team handles the execution.

~10 min read Beginner

The one-line idea

You open a GitHub issue. OpenFlows plans it, writes it, stresses it, and merges it - then tells you what happened. Coder governs where agents run; OpenFlows governs how they coordinate.

1Who it is for

OpenFlows is an enterprise-grade orchestration layer — self-hosted, governed, auditable, and multi-tenant — that is just as at home for a solo developer who wants a personal AI team. Anyone who wants AI to execute end-to-end with guardrails inside their own environment fits here:

2Prerequisites

Self-hosted Coder
OpenFlows rides on your Coder server, which provides identity, model access, and the disposable workspaces where agents run.
GitHub repository
OpenFlows turns GitHub issues into pull requests, so it needs a repository and GitHub authentication for it.
A coordination store
A shared record of truth (Redis) that coordinates the team, plus a database for Coder itself.
GitHub OAuth
OpenFlows acts on GitHub through a real identity linked via GitHub OAuth, not a shared token.

Coder governs where agents run; OpenFlows governs how they coordinate

The two systems divide the work deliberately:
  • Coder decides where work runs. It provides governed, isolated, disposable workspaces and a central model gateway where every AI call happens. Worker workspaces hold no model keys, no raw repository credentials, and no secrets.
  • OpenFlows decides how the work is coordinated. It provides the team, the planning gate, adversarial review, self-healing, and merges.
Neither replaces the other. OpenFlows does not manage machines; Coder does not write your code.

3Install & Set Up

Setting up OpenFlows means standing up the control plane (Coder, the coordination store, and a database), running the installer to bootstrap the environment, adding a tenant for your repository, and linking GitHub OAuth. From there you can open an issue and watch the team turn it into a merged pull request.

Step-by-step guidance lives on the Installation page and the First Issue Walkthrough.

4Track Your First Issue

Once the environment is up and your tenant is configured, create a clear GitHub issue in the bound repository. OpenFlows does the rest:

  1. NEXUS picks the issue up and turns it into a ticket.
  2. FORGE writes a plan, then halts.
  3. SENTINEL reviews the plan and approves it.
  4. FORGE implements, tests, and opens a pull request.
  5. SENTINEL reviews the pull request adversarially.
  6. VESSEL watches CI, resolves conflicts, and merges.
  7. LORE documents the change (where enabled).
  8. The workspace is torn down after merge - no lingering state.

If at any point OpenFlows needs a human call - a security concern, an ambiguous spec, or an unresolvable merge - you are notified and the team waits for your decision. See the First Issue Walkthrough and the Lifecycle pages for the full picture.

5What OpenFlows is not

6Next Steps

Digging deeper

Was this guide helpful?