Skip to main content
Experimental version.This is the latest in-development version of AI-Implement. Features may change without notice and behavior is not guaranteed. Switch to the latest stable version here.
Before you install AI-Implement, gather everything in the checklist below. Each item maps to a later setup step, so having them ready in advance makes the process significantly smoother.
1

Linear or Jira workspace

You need a Linear workspace where you can create labels. AI-Implement relies on the AI-Implement label to identify issues to process. You do not need admin access to the workspace — member-level access with the ability to create labels is sufficient.
2

GitHub organization or account, and a GitHub App you control

AI-Implement uses a GitHub App to authenticate workflow dispatches and to open pull requests under the app’s identity (which is what allows the /ai-implement comment trigger to work correctly). You need either:
  • A GitHub organization where you can create a GitHub App, or
  • A personal GitHub account with the ability to create a GitHub App
You will create the App during setup. See Create a GitHub App for the full walkthrough.
3

Somewhere to run the orchestrator

The orchestrator is a small Node.js service. You have two options:

Fly.io (recommended)

A Fly.io account lets you deploy the orchestrator as a managed app. The supplied deployment uses a shared-cpu-1x machine with 2 GB of memory. See Deploy the orchestrator for instructions.

Any server running Node.js

You can run the orchestrator on any server or local machine that has Node.js 24.x installed. The local development workflow is covered in Deploy the orchestrator.
4

Choose model access

For Codex, use an OpenAI API key or connect your own ChatGPT plan on Models & providers. Follow Use Codex with OpenAI after creating your project mapping. A configured project that uses Codex for every stage does not need an Anthropic credential.A connected ChatGPT plan is for personal and self-hosted use of your own account. Hosted subscription runs also require a private or internal repository authorized for subscription testing. See the Codex guide for the connection and readiness checks.If you keep a project on legacy Claude behavior, choose one of these credential paths:
These repository secrets apply to legacy Claude projects. Configured projects select a managed account profile for each stage; see Agent settings per stage.
5

A compatible runner and synced workflows

The Codex setup path uses GitHub Actions with a compatible runner image and current workflow templates. Merge the workflow pull request from project creation before opting in. For an existing project, use Sync workflows on Projects and merge that pull request first.See Runner images for compatibility checks. Managed post-push review-fix support also requires a healthy Restate connection; Managed review-fix describes the supported backend and remaining live-validation limits.
6

Node.js 24.x (for local development)

If you plan to run the orchestrator locally or contribute to the codebase, you need Node.js 24.x installed on your machine. For production Fly.io deployments, Node.js is included in the build — you do not need to install it separately.

​
What’s next

Once you have everything above, work through the setup in order:

Create a GitHub App

Create and configure the GitHub App that AI-Implement uses to authenticate with GitHub and open PRs.

Deploy the orchestrator

Run the orchestrator locally or deploy it to Fly.io.