AI-DLC Documentation
AI-DLC is a structured, gated methodology for AI-driven software development. This repository runs it natively in Claude Code, Kiro CLI, Kiro IDE, Codex CLI, Cursor, opencode, and GitHub Copilot.
Quick Start
1. Install
macOS, Linux, or WSL:
curl -fsSL https://github.com/awslabs/aidlc-workflows/releases/latest/download/install.sh | sh
Windows PowerShell:
irm https://github.com/awslabs/aidlc-workflows/releases/latest/download/install.ps1 | iex
The native installer includes every harness runtime and does not require Bun or
Node.js. On Windows, it installs for the current account and automatically
registers the bin directory in User PATH; run it from a normal PowerShell window,
since one opened with "Run as administrator" gets a warning and a prompt. If
another session cannot find aidlc, open a new terminal. Use
-NoModifyPath to skip
both persistent and current-process PATH changes.
2. Configure
Run from your project root:
aidlc config --harness claude
aidlc doctor
Replace claude with kiro, kiro-ide, codex, cursor, opencode, or
copilot. A bare aidlc config starts the interactive setup.
3. Start
Open the configured harness and describe the work:
/aidlc Build a REST API for inventory management
Codex CLI uses $aidlc. See Getting Started for
provider setup, trust prompts, project refreshes, and the first workflow.
Choose Your Harness
| Harness | Guide |
|---|---|
| Claude Code | Getting Started |
| Kiro CLI | Running AI-DLC on Kiro CLI |
| Kiro IDE | Running AI-DLC on Kiro IDE |
| Codex CLI | AI-DLC on Codex CLI |
| Cursor | AI-DLC on Cursor |
| opencode | AI-DLC on opencode |
| GitHub Copilot | AI-DLC on GitHub Copilot |
Choose Your Guide
| Guide | Use it when |
|---|---|
| User Guide | Building software with AI-DLC |
| Onboarding Walkthrough | First-time team? The mental model and a guided five-run path |
| Workflow Profiles | Choosing Classic, Express, or a focused workflow |
| Install and Lifecycle | Updating, pinning, installing offline, using mirrors, or uninstalling |
| Harness Engineer Guide | Reshaping stages, agents, scopes, rules, sensors, or knowledge |
| Development and Releases | Taking a PR through AI review, preview testing, and stable publication |
| Developer Reference | Changing the engine, hooks, packaging, or test suite |
Development
Maintainers author in core/ and harness/. Generated dist/ and
dist-release/ trees are local outputs and must not be hand-edited.
See the Contributing Guide for the development workflow and Porting to a New Harness to add another runtime.