Changelog

This version adds a Kiro submenu to the editor context menu and an Ask Kiro to Fix quick fix on errors and warnings, plus a guided form for creating hooks. Kiro moves to Code OSS v1.108.2, and now replies in your IDE display language. Chat history also survives workspace folder changes, and several sign-in, trust, and approval issues are fixed.

This version adds a guided description step to /spec new and makes Plan mode execute your approved plan automatically without a manual mode switch.

/spec new now asks what the spec should cover before drafting requirements. Instead of guessing from the spec name alone, the agent uses your description as the ground truth for the requirements it generates. Learn more ->

In Plan mode, approving a plan now kicks off execution immediately. You no longer need to manually switch modes after reviewing and accepting the plan. Learn more ->

Claude Opus 5 is now available in the Kiro IDE, CLI, and Web. It's a meaningful step up from Opus 4.8 on the hardest agentic coding tasks — setting new state-of-the-art results on leading coding benchmarks, more than doubling Opus 4.8's performance while approaching Fable 5 at half the cost. Excels at multi-file features, large refactors, and end-to-end feature work, completing full tasks rather than leaving stubs or placeholders. Opus 5 verifies its own work and iterates carefully until it succeeds. Multi-agent coordination sees meaningful gains with fewer conflicts between parallel agents. For code review, it finds a high rate of real bugs with low false positives and stays accurate at lower effort settings. Claude Opus 5 is rolling out gradually with experimental support to Kiro Pro, Pro+, Pro Max, and Power customers in us-east-1 and eu-central-1 with cross-region inference. 1M context window. 2.2x credit multiplier. Restart your IDE or CLI to access it from the model selector. Learn more ->

Your agent doesn't stop at writing code anymore. With Playwright and the agent-browser CLI available in its sandbox, it can open the app it just built in a real browser, click through the flows, reproduce browser-based bugs, and verify UI changes before you ever look. Ask for a fix and get one that's already been checked in a browser. Learn more ->

This release introduces /upgrade-agent to migrate V2 custom agent configurations to the universal format, automatic retries for interrupted model responses, and quality-of-life improvements across both modes.

Migrate V2 agent configuration files to the universal format that works with both V2 and V3. Run /upgrade-agent inside a V3 session to convert your existing custom agent configs in place the command reads your V2 configuration and produces an updated file compatible with both modes. Available in V3 mode (kiro-cli --v3). Learn more ->

This release adds user-level global hooks, a searchable session history panel, and stronger reliability for corporate proxy environments. The agent now recovers automatically from interrupted responses and refreshes MCP tools dynamically.

The moment your agent opens a pull request, it surfaces right in your session. The Reviews panel appears on its own and lists every pull request from the session; select a GitHub pull request to walk its status, commits, and changed files with unified or split diffs, all without losing your conversation. When you're ready to review or merge, one click opens it in GitHub. Learn more ->

Loading image...

This release brings two new capabilities to CLI 3.0 (early access) a built-in subagent for learning Kiro's features and global hooks that apply across all workspaces alongside error handling fixes for all users.

Ask questions about Kiro's features and get accurate answers in-line. The new introspect subagent can explain capabilities, walk you through writing custom agents, hooks, and steering files, and suggest the right configuration for your workflow. Available in V3 (kiro-cli --v3).

Define hooks once and have them apply everywhere. Hooks placed in ~/.kiro/hooks/ now fire in every workspace automatically, so cross-cutting behaviors like linting on save, security checks before commits, or custom approval gates no longer need to be duplicated per project. Workspace-level hooks continue to work alongside global ones. Available in V3 (kiro-cli --v3).

You can now connect GitLab using fine-grained access tokens. Fine-grained tokens use granular permissions instead of scopes, limiting the token to specific resources and repositories. Learn more ->

OpenAI models are available in Kiro for the first time. GPT-5.6 Sol, Terra, and Luna bring three tiers of frontier intelligence to the IDE, CLI, and Web — each tuned for a different point on the performance-cost curve. Sol is the flagship, built for the hardest multi-step work: spec-driven implementation, long-horizon refactors, and complex terminal tasks. It scores 80 on the Coding Agent Index and 88.8% on Terminal-Bench 2.1. Terra is the balanced option for routine multi-step development at a fraction of flagship cost. Luna is the fastest, lowest-cost tier for high-frequency tasks where throughput matters most. All three run longer without supervision and can write lightweight programs that coordinate tools and process intermediate results, reducing round-trips and dead ends. Hidden chain-of-thought means you see final output only. 272K context window across all tiers. Kiro credit multipliers: Sol 2.4x, Terra 1.2x, Luna 0.6x. Experimental support is rolling out to Pro, Pro+, Pro Max, and Power customers in us-east-1 and eu-central-1 with cross-region inference. Learn more ->