awslabs/aidlc-workflows

AI-Driven Life Cycle (AI-DLC) adaptive workflow steering rules for AI coding agents

AI‑DLC (AI‑Driven Development Life Cycle)

What it is

  • A framework that turns AI coding assistants (Claude, Kiro, Codex, Cursor, Opencode, GitHub Copilot) into structured, auditable software‑delivery workflows.
  • Provides a single, harness‑neutral core that runs natively inside each supported assistant, handling requirements, design, implementation, testing, and operations.

Key concepts

  • Phases & stages – 5 phases, 33 stages that guide a task from initialization to production.
  • Agents – 14 built‑in agents (domain experts, reviewers, composer) that generate and validate code.
  • Workflow profiles – Pre‑defined profiles for features, bug‑fixes, infra, security, PoCs, etc.
  • Human approval gates – Points where a developer must approve before the next automated step.
  • Audit trail – 113‑event log plus persistent state for traceability and compliance.

Supported AI harnesses

Harness Config command How to invoke
Claude Code aidlc config --harness claude /aidlc
Kiro CLI / IDE aidlc config --harness kiro (or kiro-ide) /aidlc
Codex CLI aidlc config --harness codex $aidlc
Cursor aidlc config --harness cursor /aidlc
opencode aidlc config --harness opencode /aidlc
GitHub Copilot aidlc config --harness copilot /aidlc

Installation

  • macOS / Linux / 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
  • Installs a native aidlc binary and the harness runtimes; no Bun or Node.js required.
  • For offline or custom setups, download the aidlc‑copy‑runtime‑X.Y.Z.tar.gz release and copy the runtime/<harness>/ directory into your project.

Typical workflow

  1. Configure the project for your chosen harness: aidlc config --harness <name>.
  2. Run a workflow inside the AI assistant, e.g. type /aidlc Build a REST API for inventory management.
  3. AI‑DLC selects the appropriate workflow, asks clarifying questions, and pauses at approval gates.
  4. After approvals, it generates code, tests, documentation, and deployment steps, keeping everything logged.

Development & extensibility

  • Core engine lives in core/ (TypeScript) and is harness‑neutral.
  • Harness‑specific adapters are under harness/<name>/.
  • Plugins can add custom stages or agents (plugins/).
  • Build all harnesses with Bun: bun install --frozen-lockfile && bun scripts/package.ts.
  • Comprehensive test suite (tests/) and CI scripts are provided.

Documentation & resources

  • Getting Started, User Guide, Harness Guides, and detailed developer reference are in the docs/ folder.
  • Specification PDF and AWS blog post explain the methodology.
  • The project follows the MIT‑0 license.

Who might use it

  • Teams that rely on AI coding assistants and want repeatable, auditable development pipelines.
  • Organizations needing compliance‑ready AI‑generated code with human oversight.
  • Developers who want a unified way to run AI‑driven workflows across multiple assistants.

Related

  • Project
    ai-driven-dev/framework

    An enterprise-grade SDLC framework that integrates standardized workflows, skills, and agents into AI coding tools to automate the path from idea to pull request.

  • Project
    ai-sdlc-framework/ai-sdlc

    AI‑SDLC is an open‑source decision‑engine framework that orchestrates AI‑assisted software development. It front‑loads human decisions via a Definition‑of‑Ready gate, then automatically runs a 13‑step pipeline (code generation, three independent LLM reviewers, DSSE attestation, PR creation) using an autonomous orchestrator. The system includes a terminal UI, declarative governance resources, and SDKs for TypeScript, Python, and Go. Licensed under Apache 2.0, it targets enterprises and platform teams that need reproducible, governed AI‑driven code pipelines.

  • Project
    HoangNguyen0403/agent-skills-standard

    A portable SDLC standards layer for AI coding agents that turns engineering rules into modular, version-controlled skills to reduce token usage and ensure consistent code quality.

  • Dispatch
    Integrating UML Modeling into AI-Driven Development Life Cycles

    An exploration of AI-DLC-UML, a framework designed to bridge the AI-driven software development workflow with structured UML modeling for collaborative design.

  • Project
    microsoft/hve-core

    HVE Core is Microsoft’s open‑source, AI‑augmented SDLC framework. It ships VS Code and Copilot‑CLI plugins that expose specialised agents, prompt‑based instructions and reusable “skills” to automate research, planning, coding, security checks and review. The system encodes company‑wide standards and compliance rules, letting AI carry context while humans retain judgment. Teams install the extension, invoke the RPI (Research‑Plan‑Implement‑Review) agent, and can fork/customise the repo for their own processes.