AI-Driven Development Life Cycle from AWS Labs: a harness-neutral workflow engine that turns coding agents into structured, auditable software delivery, with phases, stages, specialist agents, approval gates and persistent project state.
Follow AI-DLC to get an email when its listing changes, such as new pricing or features. One digest a day at most, and you can unsubscribe anytime.
- 01
One core that runs natively in Claude Code, Kiro IDE and Kiro CLI, Codex CLI, Cursor, opencode and GitHub Copilot
- 02
Native `aidlc` command installed via `install.sh` or `install.ps1`; `aidlc config --harness <name>` and `aidlc doctor`
- 03
5 phases and 33 stages from initialization through operation
- 04
14 agents: 11 domain experts, 2 reviewers and an adaptive composer
- 05
11 workflow profiles covering features, bug fixes, infrastructure, security, proofs of concept and enterprise delivery
- 06
Human approval gates with source-bound review evidence
- 07
Audit trail, persistent state, team knowledge and learned rules
Open Source
Free and open-source (MIT-0). Model usage is billed through whichever harness and provider you already use (for example Claude Code, Kiro, Codex or Amazon Bedrock).
Best for
Teams that want a repeatable, reviewable delivery process around AI coding agents across several harnesses, especially in AWS or Kiro environments.
Not ideal for
Quick one-off edits or solo prototyping where approval gates and a staged lifecycle add more ceremony than value.
A thorough, fast-moving spec-and-gates methodology from AWS that works across the major coding agents; heavier than lightweight spec tools, but strong on auditability.
v2.11.3 (Nov 4, 2026) ships a native `aidlc` built with Bun 1.4.4, team Units support end to end and OpenCode 2 support; 2.11.4 preview builds followed on Nov 5 and Nov 6, adding the `kiro-v2` harness name for Kiro CLI (V2).
As of
Is AI-DLC free?+
Yes - AI-DLC is Open Source. Free and open-source (MIT-0). Model usage is billed through whichever harness and provider you already use (for example Claude Code, Kiro, Codex or Amazon Bedrock).
Is AI-DLC open source?+
Yes - AI-DLC is open source. Free and open-source (MIT-0). Model usage is billed through whichever harness and provider you already use (for example Claude Code, Kiro, Codex or Amazon Bedrock).
Who is AI-DLC best for?+
Teams that want a repeatable, reviewable delivery process around AI coding agents across several harnesses, especially in AWS or Kiro environments.
Who is AI-DLC not ideal for?+
Quick one-off edits or solo prototyping where approval gates and a staged lifecycle add more ceremony than value.
What are the best AI-DLC alternatives?+
The closest AI-DLC alternatives on ai.dosa.dev are Pieces for Developers, agenttrace, Vibe Kanban - all listed under Developer Productivity & Workflow.
Who makes AI-DLC?+
AI-DLC is developed by AWS (awslabs). It is listed in the Developer Productivity & Workflow category on ai.dosa.dev.
Favorite this tool to revisit it later, or Zap it to contribute to the public vote count.