Skip to main content
Kiro

Kiro – Agentic AI‑powered IDE for Spec‑Driven Development

AI IDEaiIDEcodingdevelopmentAWS

Kiro is an agentic AI-powered IDE from AWS that uses spec-driven workflows, agent hooks, multimodal context, and transparent diffs to help developers move from prototype to production efficiently. Preview is now available.

★ 9 Last Updated: 2025-07-17 kiro.dev
Visit Website

Website Preview

Kiro — Website Preview

Detailed Introduction

Kiro – Agentic AI‑powered IDE for Spec‑Driven Development

What is Kiro?

Kiro is a next‑generation AI IDE from AWS that goes beyond simple code assistance. It uses autonomous “agents” to turn high‑level prompts into structured software systems—complete with specifications, plans, implementation, and automatic validation. It helps developers move from prototype ("vibe coding") to production-ready code.


Why Use Kiro?

  • Spec‑Driven Workflow: Generates requirements, design docs, and task plans directly from your prompt.
  • Agent Hooks: Automates repetitive tasks like test generation, documentation updates, and security checks triggered by code changes.
  • Enterprise‑Grade Structure: Maintains code consistency, prevents technical debt, and preserves developer knowledge.
  • Rich Context Management: Supports Model Context Protocol (MCP), multimodal input (images, files), steering rules, and agentic chat.

Core Features

  • Specs & Planning: Define a feature in natural language. Kiro auto-generates requirements.md, design.md, and tasks.md, with live sync as you code.
  • Agent Hooks & Automation: Event-driven agents run automatically on file save, commit, or other triggers—updating tests, docs, or scanning for issues.
  • Project Steering: Control how agents work via steering markdown files, specifying architecture, tooling, and coding standards.;
  • Autopilot & Supervisory Mode: Let agents carry out sequences of tasks automatically (Autopilot), or step through each change manually (Supervised).
  • Transparent Code Review: View agent-made changes as diffs, accept or reject each suggestion.
  • VS Code Compatibility: Runs on Code OSS and supports Open VSX extensions, themes, and developer settings.

How to Get Started

  1. Request access via the preview waitlist on kiro.dev.
  2. Download the IDE on macOS, Windows, or Linux.
  3. Open your project folder (or run kiro . in CLI).
  4. Generate steering docs to define your project's structure and standards.
  5. Create a spec: Describe a feature in chat; Kiro builds spec and tasks.
  6. Run tasks: Select a task, let Kiro generate code/tests/docs.
  7. Set up hooks: Automate docs/tests/security checks on file events.
  8. Review changes using live diffs and commit when ready.

Usage Tips

  • Start with specs for complex features—ensures clarity and maintainability.
  • Use Agent Hooks to keep tests and docs up-to-date automatically.
  • Tune project steering files to match your team's style and standards.
  • Enable Autopilot mode for faster execution, or stay in Supervised mode when precise control is needed.

FAQ

Q: Is Kiro free?
A: During public preview, Kiro is free. Post-preview pricing: a free tier with 50 agent interactions/month, Pro (\(19/mo for 1,000), and Pro+ (\)39/mo for 3,000).

Q: How is it different from GitHub Copilot?
A: Copilot provides inline code completions. Kiro goes further—it understands feature goals, works across multiple files, generates specs, automates tasks, and provides agents.

Q: Does it run locally?
A: Yes, the IDE runs locally. AI processing can happen in the cloud, but all code stays on your machine unless opted in.

Q: What AI models does it support?
A: Currently powered by Anthropic Claude Sonnet (3.7 & 4.0). More models expected soon.

Q: Can I use it with existing VS Code setups?
A: Yes. Kiro supports VS Code themes and Open VSX extensions.

Jules - Google's AI Coding Assistant for Automating Development Tasks

Jules is Google's AI-powered coding assistant designed to automate routine development tasks such as bug fixes and version updates. Integrated with GitHub and powered by Gemini 2.5 Pro, Jules operates asynchronously to enhance developer productivity

aiagentgoogle

Lingma by Alibaba Cloud – AI-Powered Coding with IDE and Plugin Support

Lingma is an AI-powered coding assistant developed by Alibaba Cloud. It supports both plugin-based integration with VS Code/JetBrains and a newly launched standalone IDE for Windows and macOS. With intelligent code generation, error debugging, cross-file refactoring, and enterprise-level deployment, Lingma helps developers write better code faster—especially in Chinese-language development environments.

aifreealibaba

Open Lovable – Open Source AI-Powered Website-to-React Converter

Open Lovable is an open-source project by Mendable AI that lets developers clone any website and convert it into a React app using AI, powered by Firecrawl, Groq/Moonshot AI, and E2B sandbox. Free, self-hosted, and privacy-friendly.

open lovableopen-lovablewebsite to React

Qwen3-Coder One of the Strongest Open Source Programming Models

Qwen3-Coder is a large-scale open-source programming model launched by Alibaba Cloud's Qwen team, featuring Agentic intelligence capable of automating software development tasks, supporting ultra-long contexts and multiple programming languages.

AI Programming ModelOpen Source ProjectSmart Assistant

OpenRouter - A unified interface for LLMs

OpenRouter is a unified interface that provides access to a wide range of large language models (LLMs) from various providers, including both proprietary and open-source models. It offers better prices, improved uptime, and does not require a subscription.

ai

OpenAI Platform

Playground is an online interactive tool provided by OpenAI for testing and exploring the capabilities of its language models (such as GPT-3.5, GPT-4, GPT-4o). It is particularly suitable for developers, content creators, product managers, and anyone who wishes to interact with AI models without writing code.

aideveloper