Changelog

This release makes Kiro Specs faster to start, faster to finish, and harder to get wrong. Run independent tasks concurrently for faster execution, skip approval gates with Quick Plan when you already know the scope, and catch logical inconsistencies in your requirements before they become implementation problems.

Run all Tasks now runs independent tasks concurrently instead of one at a time. No configuration needed - click Run all Tasks and Kiro handles the rest. It analyzes your task list for dependencies and groups independent tasks into parallel waves, each running in its own isolated context. For specs with 4+ independent tasks, this can cut execution time by up to 4x. Learn more ->

A new Spec session mode for when you already know what you want to build. Kiro generates requirements, design, and tasks in a single pass without approval gates between phases. It asks clarifying questions up front (scope, constraints, edge cases) then produces all three artifacts. You land directly on the task list, ready to build. Same traceability and correctness that Specs provide, with a tighter feedback loop. Learn more ->

A deep analysis pass that catches logical inconsistencies, ambiguities, conflicting constraints, and gaps in your requirements before you move to design. Kiro uses automated reasoning to find issues that are hard to catch in a read-through - ambiguous language, conflicting constraints, and logical gaps. Results appear in chat as clarifying questions you can resolve in seconds. Learn more ->

This release adds adaptive thinking support so model reasoning carries across turns in a conversation, giving you more coherent answers as context builds. It also fixes a silent failure in subagent tool dispatch when MCP servers update their tool specs mid-execution.

Kiro CLI now preserves model reasoning across multi-turn conversations. Thought content from earlier turns stays available to the model on subsequent turns, so follow-up answers stay aligned with the reasoning that produced previous responses. You get more coherent multi-step workflows without re-explaining context.

This release focuses on keeping you in flow: shell output streams as it happens, Tool Search loads MCP tools on demand so your context window stays clear, and skills are now invokable as slash commands. This release also adds device flow authentication for remote environments, RHEL support, and several rendering and stability fixes.

Shell command output now streams to the terminal line by line as it runs, instead of buffering until the process completes. Long-running commands like builds, test suites, and deployments show progress immediately, so you can follow along and catch issues early. Learn more ->

Tool Search loads MCP tools on demand instead of sending every definition with each request, keeping your context window clear when you have many MCP servers configured. Enable it with kiro-cli settings toolSearch.enabled true. Learn more ->

Skills defined in .kiro/skills/ are now available as /skill-name slash commands. Type / and the skill name to invoke it directly, giving you quick access to reusable agent instructions without switching agents or copying instructions into your prompt. Learn more ->

Sign in with Google or GitHub from SSH sessions, containers, and cloud workspaces without port forwarding. The CLI displays a URL and one-time code you enter in any browser — same flow as Builder ID and IAM Identity Center. Learn more ->

Kiro CLI's terminal UI now runs on Red Hat Enterprise Linux (RHEL). If you're working in enterprise Linux environments, you get the same full-featured terminal UI experience available on other Linux distributions, macOS, and Windows. Learn more ->

The daily user activity report now breaks down message counts by AI model, so enterprise admins can track model adoption and understand how usage maps to specific models. Each model used during the reporting period gets its own column (e.g., Auto_messages, Claude_Opus_4.6_messages). Learn more ->

Added support for Claude Opus 4.7, Anthropic's latest Opus model with stronger agentic coding performance, more precise instruction following, and 3x higher resolution vision. Rolling out with experimental support to a subset of Pro, Pro+, and Power tier subscribers signing in with AWS IAM Identity Center, with broader availability to follow. Support for Google, GitHub, and AWS Builder ID sign-in is coming soon. 1M token context window with a 2.2x credit multiplier. Inference runs in us-east-1 (N. Virginia) and eu-central-1 (Frankfurt). Restart your IDE or CLI to access it from the model selector. Learn more ->

The Users and Subscriptions tabs in the Kiro console now display an Email column for teams using IAM Identity Center, making it easier to identify and manage team members. Admins can see each user's email address alongside their username and plan details. The email field is also included when downloading the subscriptions CSV file. Learn more ->

Kiro CLI 2.0 expands platform support to Windows, introduces headless mode for CI/CD automation, graduates the terminal UI from experimental to the default experience, and adds new capabilities across subagents, hooks, and MCP configuration.

Kiro CLI now runs natively on Windows 11. Windows users can now build using the same agentic coding experience available on macOS and Linux — terminal UI, headless mode, custom agents, and MCP servers all included. Install from PowerShell and background auto-updates keep you current. Learn more ->

Run Kiro CLI non-interactively in CI/CD pipelines, automation scripts, and environments without a browser. Authenticate with an API key via the KIRO_API_KEY environment variable, pass a prompt with --no-interactive, and Kiro executes it end-to-end. Use --trust-all-tools or --trust-tools to grant tool permissions upfront. API key authentication is available for Pro, Pro+, and Power subscribers, and enterprise admins can control API key generation through governance settings. Learn more ->

The terminal UI is now the default chat interface. It gives you syntax-highlighted markdown, interactive overlay panels, visual tool progress, and a full set of keyboard shortcuts. Use the crew monitor (Ctrl+G) to track subagent activity in real time, /theme to customize colors, /copy for clipboard access over SSH, /transcript to review conversation history in your pager, /guide to switch to the onboarding agent, and /spawn to run parallel agent sessions. Subagents now support task dependencies — for example, analyze a codebase first, then refactor modules, then run tests, with each step waiting for the previous one to finish while independent steps run in parallel. Switch back to the classic interface anytime with --classic or kiro-cli settings chat.ui "classic". Learn more ->

Added support for GLM-5, a sparse mixture-of-experts model with a 200K context window designed for complex systems engineering and long-horizon agentic tasks. GLM-5 excels at processing repository-scale context and maintaining coherence during multi-step tool use across large codebases, making it a strong choice for cross-file migrations, full-stack feature development, and legacy refactoring where the model needs to hold the full picture. Available with experimental support in both the Kiro IDE and Kiro CLI. Inference runs in us-east-1 (N. Virginia) with a 0.5x credit multiplier. Restart your IDE or CLI to access it from the model selector. Learn more ->

Administrators can now export Kiro subscription data as a CSV file directly from the Kiro Console. The new "Download CSV" button on the Users & Groups page's Subscriptions table exports user name, subscription plan, status, type, and activation date.

Claude Opus 4.6 and Claude Sonnet 4.6 now support a 1M context window, up from 200K, and are no longer marked as experimental. Both models are now generally available in the Kiro IDE and Kiro CLI for Pro, Pro+, and Power tier subscribers.

Restart your IDE or CLI to see the updated models. Learn more ->