Skip to main content
Tgtoolglade.
K

Kiro

AWS's agentic, spec-driven AI IDE that plans before it codes.

Hand-reviewed by the Toolglade team·Updated Aug 2026
coding#write-code
Visit Website
Free plan Teams Mobile app
Toolglade’s take

A credible, GA-stage agentic IDE whose spec-first workflow pays off on substantial features and team work, though the credit model and planning overhead won't suit quick edits.

About Kiro

Kiro is Amazon Web Services' agentic development environment built around spec-driven development, where an AI agent turns your idea into structured requirements, a design doc, and a tracked task list before writing code. Built on the VS Code-based Code OSS platform, it adds specs, hooks, steering files, and custom agents. Kiro is generally available and is AWS's successor to Amazon Q Developer.

Kiro is an agentic AI IDE from AWS that makes specifications, rather than one-off prompts, the unit of work. Instead of jumping from a chat prompt to a diff, Kiro first generates a requirements file, a design document, and a discrete task plan that you review and approve, then executes independent tasks in parallel. Built on Code OSS (the same foundation as Visual Studio Code), it layers on hooks for event-driven automation, steering files for persistent project context, custom subagents with scoped permissions, and MCP integrations. It runs on a credit-based freemium model with a perpetual Free tier and paid plans from $20/month, uses a default Auto agent that blends frontier models like Claude Sonnet with specialized models, and reached general availability in 2026 as the replacement for Amazon Q Developer.

TL;DR

Kiro is AWS's agentic, spec-driven AI IDE and the successor to Amazon Q Developer. Built on the VS Code-based Code OSS platform, it turns prompts into structured requirements, design docs, and tracked tasks before generating code, and adds hooks, steering, and custom agents. It runs on a credit-based freemium model with a perpetual Free tier and paid plans from $20/month, defaulting to an Auto agent that blends models such as Claude Sonnet. Generally available since 2026, it targets professional and enterprise teams that value planning and repeatability.

Company overview

Kiro is a product of Amazon Web Services (AWS), the cloud division of Amazon. It is not a startup but a first-party AWS offering, developed and operated by Amazon and positioned as the successor to Amazon Q Developer (itself the evolution of Amazon CodeWhisperer).\n\nAWS reached general availability for Kiro in May 2026 and is steering existing Amazon Q Developer customers toward it, with the newest coding models offered through Kiro. The product spans a desktop IDE, a CLI, and preview web and mobile clients, backed by AWS's enterprise, security, and compliance infrastructure.

Product features

Kiro's defining feature is spec-driven development: each feature starts as a requirements file, a design document, and a discrete, trackable task list that you approve phase by phase, after which independent tasks run concurrently in dependency-ordered waves. Quick Spec and Bugfix Specs adapt the workflow for well-understood changes and root-cause bug fixes.\n\nAround the spec workflow, Kiro adds hooks (event-driven automations that trigger the agent on actions like saving a file), steering files (persistent project context and conventions), custom subagents with scoped tool permissions, MCP integrations, Agent Skills, Powers, checkpoints and rewind, and cloud sessions. It is built on Code OSS, so it retains a familiar VS Code-style editor and extension model.

Target market

Kiro targets professional and enterprise software teams that prioritize planning, consistency, and reviewability over raw generation speed, especially organizations already invested in AWS or migrating off Amazon Q Developer. Its hooks, steering, SSO, usage analytics, centralized billing, VPC endpoints, and GovCloud availability appeal to regulated and larger engineering organizations, while the perpetual Free tier and simple sign-in also make it accessible to individual developers evaluating spec-driven workflows.

Buyer personas

End users

Software developers and engineering teams who build and maintain non-trivial features and want an AI agent that plans, documents, and tracks its work rather than improvising.

Buyers

Engineering leaders, platform and developer-productivity teams, and IT procurement at companies standardizing on AWS or transitioning from Amazon Q Developer.

Key influencers

Staff and principal engineers, DevEx and platform teams, AWS solutions architects, and internal AI-tooling champions who evaluate agentic IDEs.

Ideal customer profile

AWS-aligned professional or enterprise engineering teams that want structured, spec-driven AI development with enforceable standards and enterprise controls.

Funding & performance

Kiro is not a venture-funded startup; it is a first-party product of Amazon Web Services, part of Amazon (NASDAQ: AMZN). It is developed, funded, and operated internally by AWS and benefits from Amazon's cloud infrastructure, model access, and enterprise go-to-market. As such, questions of external funding rounds or investors do not apply; its resourcing and roadmap are backed by Amazon rather than outside capital.

Pros & cons

Pros

  • Spec-driven workflow produces reviewable requirements, design, and task artifacts
  • Familiar Code OSS (VS Code-based) editor and extension compatibility
  • Hooks and steering files encode team standards and persistent context
  • Parallel task execution speeds up larger features
  • Backed by AWS with strong enterprise and compliance controls
  • Access to leading models, including Claude Sonnet and Opus, via the Auto agent

Cons

  • Spec ceremony is overhead for small or exploratory changes
  • Credit-based pricing makes costs hard to predict on large tasks
  • Unused monthly credits do not roll over
  • Pinned premium models consume credits noticeably faster than Auto
  • Younger product whose pricing has already shifted more than once
  • Web and mobile clients remain in preview

Pricing plans

Free
$0 / month
  • 50 credits per month (perpetual)
  • Access to Claude Sonnet 4.5 and open-weight models (rate-limited)
  • Full spec-driven IDE, hooks, and steering
  • Sign in with Google, GitHub, or AWS Builder ID
  • Bonus credits for new users during evaluation
Pro
$20 / month
  • 1,000 credits per month
  • Access to premium models, including Auto, Claude Sonnet 4.6, and Opus
  • Add-on credits / overages at $0.04 per credit
  • $20 credit toward your first paid month
Pro+
$40 / month
  • 2,000 credits per month
  • Access to premium models
  • Add-on credits / overages at $0.04 per credit
  • For heavier individual spec and agent usage
Power
$200 / month
  • 10,000 credits per month
  • Access to premium models
  • Add-on credits / overages at $0.04 per credit
  • Highest individual capacity (a $100 Pro Max tier with 5,000 credits also exists)

Key features

Mobile app
Team collaboration
Multi-language
Integrations
Model Context Protocol (MCP), GitHub, AWS IAM Identity Center, VS Code extensions (Code OSS), AWS Builder ID / Google sign-in
Input types
text, code
Output types
code, text
Best For
Spec-driven feature development, Enforcing team coding standards, AWS-aligned engineering teams

Compare key features

View all alternatives →
Feature
Kiro
GitHub Copilot
Replit AI
Pricing
Freemium
Freemium
Freemium
Free plan
Yes
Yes
Yes
Free trial
No
No
No
Team support
Yes
Yes
Yes

Frequently asked questions

What is Kiro?+

Kiro is AWS's agentic, spec-driven AI IDE. Built on the VS Code-based Code OSS platform, it turns your idea into structured requirements, a design document, and a tracked task list before generating code, and adds hooks, steering, and custom agents. It is the successor to Amazon Q Developer.

Is Kiro free?+

Yes. Kiro has a perpetual Free tier with 50 credits per month, plus paid plans starting at $20/month (Pro) and ranging up to $200/month (Power). New users also receive bonus credits for evaluation.

Do I need an AWS account to use Kiro?+

No. You can sign in with a Google account, GitHub, an AWS Builder ID, or AWS IAM Identity Center. An AWS account is optional for individual developers.

Which AI models does Kiro use?+

By default Kiro uses Auto, an agent that blends frontier models such as Claude Sonnet with specialized models. You can also pin a specific model, including Claude Sonnet 4.5/4.6, Opus variants, or open-weight models, though premium models consume credits faster.

How is Kiro different from Cursor or GitHub Copilot?+

Cursor and GitHub Copilot focus on fast inline completion and chat within the editor. Kiro emphasizes a spec-first workflow that generates and approves requirements, design, and tasks before writing code, aimed at predictable, reviewable output for larger features and teams.

Is Kiro replacing Amazon Q Developer?+

Yes. AWS has placed Amazon Q Developer on an end-of-support path and directs developers to Kiro, where its newest coding models are offered. Existing Q Developer customers are encouraged to plan a migration.

Reviews (0)

Write a review

Pick a rating
Loading reviews…
Compare

Compare Kiro with other AI tools

Side-by-side pages for pricing, features, and best-fit use cases.

All comparisons →
Compare side by side

Kiro vs GitHub Copilot

Compare →
Compare side by side

Kiro vs Replit AI

Compare →
Compare side by side

Kiro vs Tabnine

Compare →
Compare side by side

Kiro vs Cursor

Compare →
Compare side by side

Kiro vs Windsurf

Compare →
Compare side by side

Kiro vs Lovable

Compare →

From the blog

All articles →
Article

Kiro Review (2026): AWS's Spec-Driven AI IDE, Tested

Hand-reviewed look at Kiro, AWS's agentic spec-driven AI IDE: how specs, hooks, and agents work, credit-based pricing from $20/month, strengths, limits, and rivals.

Read →

Similar tools you may like