About
Kiro helps developers and teams turn prompts into executable specs. It produces requirements, architectural designs, and sequenced tasks, then implements them with parallel agents, either on your local machine or in the cloud. Before writing code, Kiro checks requirements for contradictions and gaps using automated reasoning.
Kiro checks behavior with property-based tests, which assert rules that must hold across all inputs instead of a few examples. This is meant to catch edge cases that pass unit tests but fail in production. You can also pull context from tools like Figma or Terraform, and run the headless Kiro CLI in CI/CD to review PRs and fix bugs without opening an editor.
Kiro supports Agent Client Protocol (ACP), AGENTS.md, Skills.md, and MCP, and the Kiro IDE supports Open VSX extensions and VS Code settings. Model selection includes Anthropic Claude, OpenAI GPT, and open-weight models, or Auto, which picks a model based on task complexity. Kiro uses credit-based pricing with no daily or weekly rate limits.
What's new
All release notesHomebrew cask kiro 1.4.62 (sha256 84fbe496842f8d63fea25b7a2534ac55fc1696217717f9fb42b69ba9b719bbeb).