AI-DLC Workflows

Overview

AI-DLC Workflows, also called AI-Driven Development Life Cycle, is a structured, gated methodology for AI-driven software development. It provides a harness-neutral core that runs natively in Claude Code, Kiro CLI, Kiro IDE, Codex CLI, Cursor, opencode, and GitHub Copilot, keeping requirements, decisions, implementation, tests, and operational work connected through an audited lifecycle.

Key Features

• Five phases and 33 stages from initialization through operation.
• Fourteen agents, including 11 domain experts, 2 reviewers, and an adaptive composer.
• Eleven workflow profiles for features, bug fixes, infrastructure, security, proofs of concept, enterprise delivery, and other common work.
• Human approval gates and source-bound review evidence.
• A 119-event audit trail plus persistent state, team knowledge, and learned rules.
• The same deterministic engine across every supported harness.

Use Cases

• Building software with AI-assisted workflows.
• Fixing bugs and delivering infrastructure or security work through focused workflow profiles.
• Running proofs of concept and enterprise delivery with approval gates and audit evidence.
• Onboarding teams through a guided first week and first workflow.

Getting Started

• Install AI-DLC with the native installer for macOS, Linux, WSL, or Windows PowerShell.
• From the project root, run aidlc config --harness <harness>, replacing <harness> with claude, kiro, kiro-ide, codex, cursor, opencode, or copilot.
• Run aidlc doctor to check the setup.
• Open the configured harness and invoke /aidlc with a work request; Codex CLI uses $aidlc.

Deployment & Requirements

• The native installer sets up the aidlc command and every harness runtime; Bun and Node.js are not required for the native install.
• The manual-copy alternative requires Bun and copying the complete runtime/<harness>/ directory into the project.
• On Windows, run the installer from a normal PowerShell window and reopen any already-open terminal or IDE before using aidlc.

Before You Adopt

• License: MIT-0. Review its terms before using, modifying, or distributing the project.
• Amazon Bedrock access depends on enabling the configured models and verifying AWS credentials and region.
• On Windows, run the installer from a normal PowerShell window because an administrator-opened session receives a warning and a prompt.