This release addresses critical security vulnerabilities and bug fixes.
Security Improvements
V8 Engine Security: Merge Chromium 138.0.7204.251 to address CVE-2025-10585, a zero-day vulnerability addressing type confusion issue in V8 JavaScript and WebAssembly engine.
Command Execution Security: Fixed vulnerability on PowerShell that could allow malicious commands to execute without user confirmation
Bug Fixes
License Access: Fixed render issue in License page
This release brings Auto, our new agent, enhanced usage tracking, and editor improvements to elevate your development experience.
New Features
Note: These features are rolling out gradually between now and October 1st, and users will be migrated to a single pool of credits and new limits. Your limits will reset to the new monthly plan limits once migrated.
Auto: Added Auto to the model options. Auto is an agent that uses a mix of different frontier models such as Sonnet 4 combined with specialized models, and optimization techniques such as intent detection, caching, and more
Unified Limits: Support for new paid plans with unified limits and fractional credit consumption
Usage Dashboard: Support to view usage based on single Kiro credit pool
Usage Meter: Add credit consumption status bar item to allow easier usage tracking
Bug Fixes and Improvements
Editor Upgrade: Upgraded editor to CodeOSS 1.103.2
Account Management: Enable Kiro account deletion for BuilderID
Authentication: Improvements to login reliability and logout flow for better signing experience
UI Improvements: Hide trust command UI on command cancellation
This release includes editor performance improvements, enhanced reliability, and bug fixes to enhance your development experience.
Performance & Reliability
Code OSS v1.100.3 Upgrade: Updated to Code OSS v1.100.3 that adds improved stability and performance improvements
Faster Response Times: Optimized request handling makes interactions more efficient and improves performance
Improved Session Management: Enhanced backend processing reduces interruptions and allows for longer continuous work sessions
Enhanced User Experience
Enhanced Tool Call Recovery: When tool invocations result in repeated failures, Kiro now prompts for your intervention instead of continuing indefinitely, protecting your usage limits and preventing loops
Enhanced Security Patterns: Expanded detection of dangerous shell commands with improved pattern recognition. Risky commands require manual review unless you explicitly trust them. Learn more about security patterns →
Model Update: Removed Claude Sonnet 3.7 from the model selector and set Claude Sonnet 4 as the default for all users. Sonnet 4 delivers improved performance and capabilities across all interactions.
Bug Fixes
Git Repository Initialization: Fixed issue that prevented Git setup for new projects without existing repositories
Model Selection Persistence: Fixed chat model selection not being saved when restarting Kiro IDE
This release brings key improvements to accessibility, account management, and overall platform reliability.
🎟️ Waitlist Code Support
Kiro is now accessible to more developers through waitlist codes. If you have an waitlist code, you can register and start building with AI-powered development workflows alongside our growing community.
💳 Paid Plans Now Available
Paid plans are now live, giving you access to higher usage limits. Choose the plan that fits your development needs and scale your AI-powered workflows.
📊 Usage Tracking & Billing Dashboard
Introducing comprehensive usage tracking to help you monitor your Kiro consumption. The new billing dashboard displays real-time spec and vibe request usage, plan management options, and overage controls for paid plans.
Kiro, a new agentic IDE that helps you do your best work with spec-driven development.
Features
Specs
Structured artifacts that formalize the development process for complex features in your application. Learn more
Video transcript
The video shows the Kiro IDE. In the left sidebar under "SPECS", the user clicks "simple-todo-app", which opens a "requirements.md" file titled "Requirements Document" containing an introduction and numbered requirements written as user stories with WHEN/THEN acceptance criteria. A row of tabs reads "1 Requirements", "2 Design", "3 Task list"; the user clicks "2 Design" to reveal a "design.md" file with a layered architecture diagram (User Interface, Application Logic, and Data Layer) and component definitions. The user then clicks "3 Task list" to show a "tasks.md" implementation plan of checkboxed tasks, where the first task is marked "Task completed" and later tasks show "Start task" actions.
Hooks
Set up event-driven automation like updating documentation or generating tests on events such as file save. Learn more
Video transcript
The video shows the Kiro IDE. In the left sidebar under "AGENT HOOKS", the user clicks "Code Quality Analyzer", opening its configuration editor for the file ".kiro/hooks/code-quality-analyzer.kiro.hook" with a "Hook enabled" toggle switched on. The panel shows the hook's title and a description ("Monitors source code files for changes and analyzes modified code for potential improvements..."), an "Event" selector with "File Saved" chosen among the options File Created, File Saved, File Deleted, and Manual Trigger, and a "File path(s) to watch" list of glob chips covering JavaScript, TypeScript, JSX, TSX, Python, Java, and C++ files. Below, an "Instructions for Kiro agent" text area lists what to analyze — code smells and anti-patterns, design patterns, language best practices, readability, maintainability, and performance.
Steering
Define steering files to guide agent behaviors. Learn more
Video transcript
The video shows the Kiro IDE. In the left sidebar under "AGENT STEERING", the user clicks through three markdown files. "product.md" opens to a "Product Overview" describing the workspace as a development environment configured for AI-assisted coding with Kiro. "structure.md" shows a "Project Structure" document with a directory tree of the ".kiro/" folder (hooks, specs, and steering subfolders) and file-naming conventions. "tech.md" shows a "Technology Stack" document listing the IDE, platform (macOS), shell (zsh), and common shell commands.
Agentic chat
Build features from chat. Turn on Autopilot mode for hands-off execution or approve each change manually. Learn more
Video transcript
The video shows the Kiro IDE with the "Let's build" chat panel open on the right, using the "Claude Sonnet 4.0" model with "Autopilot" enabled. The user types "Help me get started on the next task" and sends it. Kiro responds by first "Including Steering Documents" — shown as chips for product.md, structure.md, and tech.md — then replies that it sees an existing spec at ".kiro/specs/simple-todo-app" and will check its contents to identify the next task, displaying a "Searched workspace" step while it works.
MCP
Integrate with your favorite tools and services. Learn more
Video transcript
The video shows the Kiro IDE. In the left sidebar, the "MCP SERVERS" section lists "aws-docs" (Connected), "github" (Connected), and "my-remote-mcp" (Disabled). The user expands "aws-docs" to reveal its tools — read_documentation, search_documentation, and recommend — and opens the "mcp.json" configuration file, which defines each server's command, arguments, and environment (for example, aws-docs runs via "uvx" and github via "npx" with a personal access token). Finally, in the chat input the user invokes a tool by typing "#[aws-docs] read_documentation" and pressing Enter.