AWS has open-sourced Kiro Crew, an orchestration platform that turns AI coding agents into persistent engineering teams while giving enterprises greater control over governance, security and compliance through self-hosted deployments.
AWS has released Kiro Crew as an open-source orchestration platform designed to transform AI coding assistants into persistent, autonomous engineering teams that can manage long-running software development workflows across multiple sessions. Unlike conventional coding assistants, Kiro Crew coordinates multiple AI agents, preserves project memory, schedules recurring work, integrates with developer tools, investigates incidents, monitors pull requests, triages tickets and automates engineering tasks.
AWS has also introduced open-source reference applications built on Kiro Crew, including DevFleets for worktree management, Issue Radar for issue and pull request triage, and Task Runner for executing long-running engineering tasks.
“Kiro Crew is a persistent, open-source development workspace for work that is bigger than a single task in a single session. Think of it as an application layer that turns AI coding agents into always-working, self-learning, autonomous teammates,” said Darko Mesaros, Distinguished Developer Advocate at AWS.
Analysts said the platform could benefit DevOps, platform engineering and Site Reliability Engineering teams by automating tasks such as dependency upgrades, framework migrations, incident investigations and ticket routing, allowing developers to focus on higher-value engineering work.
Being open source and self-hostable enables organisations to keep source code, credentials and AI workflows within their own infrastructure, strengthening governance, security and compliance. Kiro Crew supports open standards including Agent Client Protocol (ACP) and Model Context Protocol (MCP), although its initial release depends on AWS’s proprietary Kiro CLI, meaning organisations using other AI coding agents may require custom connectors. AWS said the project will operate under an open governance model with a public steering committee and community maintainers over time.
