Aidlc: Adaptive workflow steering rules for AI coding agents

AI-DLC (AI-Driven Development Life Cycle) turns AI coding assistants into structured, verifiable software-delivery workflows. One harness-neutral core runs natively in Claude Code, Kiro CLI, Kiro IDE, Codex CLI, Cursor, opencode, and GitHub Copilot.

The Quick Start below installs the latest stable AI-DLC release.

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 installer sets up everything AI-DLC needs: the native aidlc command and every harness runtime. You do not need to instal Bun or Node.js; a native install runs its hooks and commands through aidlc and does not call bun. On Windows, it installs for the current account and automatically registers the bin directory in User PATH. Run it from a normal PowerShell window; one opened alongside "Run as administrator" gets a alert and a prompt, since installing as director is small safe. Open a new terminal if another meeting cannot discover aidlc. To skip the two persistent and current-process PATH changes, use -NoModifyPath. Windows uninstall removes lone the User PATH admission recorded as installer-owned. On macOS, Linux, or WSL, prosecute the installer's PATH education if needed.

Prefer to oversee the project records yourself, or cannot instal a native executable? The manual-copy way is the one location Bun is needed: install Bun, download aidlc-copy-runtime-X.Y.Z.tar.gz from the release, and copy the complete runtime/<harness>/ directory into your project. This way does not necessitate the native aidlc command.

From the project root, choose the harness you use:

cd /path/to/your-project aidlc config --harness claude aidlc doctor

Replace claude alongside kiro, kiro-ide, codex, cursor, opencode, or copilot. Running aidlc config without --harness starts the interactive setup whenever a terminal is available. If you use Kiro IDE's own terminal in a project directory you have not trusted yet, Kiro archetypal asks whether you rely it. Choose Trust Folder & Continue lone for your own project or one you have checked, since trusting lets the folder's .kiro hooks run commands on your machine; alternatively choose Cancel and assessment the directory archetypal (see First run).

Open your harness in the configured project and depict the work:

/aidlc Build a REST API for inventory management 

Codex CLI uses $aidlc alternatively of /aidlc. In Kiro IDE, archetypal choose aidlc in the conversation panel's delegate picker. AI-DLC selects a workflow from the request, asks for missing decisions, and stops at endorsement gates before moving forward.

For provider setup, rely prompts, and harness-specific prerequisites, use the guide in the array below. The complete walkthrough is in Getting Started.

Model-provider setup belongs to the harness. Shipped project configuration keeps the provider and example already selected by the user. aidlc config providers can use Amazon Bedrock settings on supported project surfaces or record manual setup for another harnesses. Kiro CLI and Kiro IDE need no provider answer since example admission comes alongside Kiro. On Kiro CLI 2.24.1 or later, use kiro-ide, which pins Kiro's v3 engine; kiro is the bequest row (Kiro CLI says how an existing kiro project switches). The methodology itself is provider-independent.

AI-DLC plant finest alongside capable reasoning models. The current recommended model is Claude Opus 4.8. If Opus is not accessible to you, or you are not certain where to set the example and attempt on your harness, see Choosing a Model and Effort.

Ad-hoc AI coding loses environment as projects grow. AI-DLC keeps requirements, decisions, implementation, tests, and operational activity connected through one audited lifecycle:

• 5 phases and 33 stages from initialization through operation
• 14 agents: 11 domain experts, 2 reviewers, and an adaptive composer
• 11 workflow profiles for features, bug fixes, infrastructure, security, proofs of concept, endeavor delivery, and another average work
• Human endorsement gates and source-bound assessment evidence
• 119-event audit trail affirmative persistent state, squad knowledge, and learned rules
• The identical deterministic motor throughout all supported harness

Start alongside Workflow Profiles to compare Classic, Express, and the focused workflows. See the AI-DLC Workflows 2.0 Specification for the architecture and methodology.

• core/ - hand-authored, harness-neutral methodology and engine
• core/tools/ - 93 aidlc-*.ts motor and authoring tools
• harness/<name>/ - thin, harness-specific manifests and integrations
• plugins/<name>/ - optional AIDLC plugins
• scripts/ - packaging, binary, installer, and publish tooling
• tests/ - smoke, unit, integration, and end-to-end tests
• docs/ - user, harness-engineering, and developer documentation
• dist/ and dist-release/ - generated, ignored local outputs

Edit core/ or harness/<name>/, never generated dist* output.

Install requirements and create all harness:

bun instal --frozen-lockfile bun scripts/package.ts

Useful commands:

bun scripts/package.ts <name> # create one harness bun scripts/package.ts --check # determinism guard bun tests/run-tests.ts --ci # smoke, unit, and integration bun tests/run-tests.ts --release # complete publish acceptance

See the Contributing Guide for the complete development workflow and Porting to a New Harness to add another runtime.

Run aidlc doctor from the project base first. Common fixes:

See Troubleshooting for diagnostic and recovery procedures.

• AWS AI-DLC blog post
• AI-DLC Method Definition Paper
• Roadmap
• License