Kiro Release Notes

This release lets you talk to Kiro instead of typing: /voice dictates your prompts with on-device transcription. Spec runs gain a review screen for reading phase documents and staging line comments, and AGENTS.md files now load as steering context from anywhere in your workspace tree. Enterprise administrators should note that cloud sessions are now opt-in, so organizations that never set the toggle will find them disabled.

/voice dictation

Speak your prompts instead of typing them. Start a recording with /voice, Ctrl+O, or by holding Space, and partial text streams into the prompt as you talk until you press Enter or it auto-stops on silence. By default your speech is transcribed on your own machine with Whisper, so no audio leaves your computer and no cloud API key is required. The model downloads once, behind an explicit confirmation, on first use. Add --continuous for a hands-free back-and-forth that starts a new recording each turn.

Cloud sessions are now opt-in (v3)

Cloud sessions are now disabled unless an administrator explicitly turns on Cloud Sessions in the Kiro console. Because an unset toggle now resolves to disabled, organizations that never configured it will find cloud sessions unavailable until an admin opts in.

Spec review screen (v3)

Press Ctrl+X at a spec phase checkpoint to read the phase document in place and stage line comments on the parts you want changed. When you answer the checkpoint question, every staged comment goes to the agent as one revision request, so reading a document and asking for changes stays in a single screen.

Nested AGENTS.md steering (v3)

AGENTS.md files now load as steering context from anywhere in your workspace tree, not just the workspace root and ~/.kiro/steering/. Put an AGENTS.md next to the code it describes, and the agent picks it up alongside your other steering files.

This release introduces cloud sessions in preview: run your session in a managed cloud sandbox with --cloud, disconnect while the agent keeps working, and resume from any machine. The slash command menu also gains substring matching, and typing in the TUI stays smoother during rapid input.

Cloud sessions (preview)

Cloud sessions let you run Kiro CLI in a managed cloud sandbox instead of on your machine. Start one with kiro-cli --cloud (or kiro-cli chat --cloud), attach repositories with --repo or the /repo picker, then disconnect while the agent keeps working and resume later from any machine with --resume-id. Cloud and local sessions appear together in the session picker.

This version brings Cloud Sessions to Agent Focus Mode as a preview and gives the sessions rail a collapsible icon-only view, attention cards you can answer in place, and back/forward navigation. It also pins the agent's Windows terminal to PowerShell, restores Always Allow for commands it was quietly forgetting, and fixes the macOS updater downloading every update twice.

Cloud Sessions in Agent Focus Mode

Cloud Sessions are now available in Agent Focus Mode as a preview. Start a session that runs in the cloud alongside your local ones, pick the repositories it works against, and keep those repositories visible below the chat. Cloud sessions use the same agent and model selectors as local sessions.

Agent Focus Mode: collapsible rail, attention cards, and navigation

Collapse the sessions rail to an icon strip to give the chat more room, with every session still one click away. When a session needs your input, an attention card appears next to the chat with the question and the agent's options as buttons, so you can answer it without switching over. The attention panel never opens on its own, and won't raise itself for the session you already have on screen. And you can move back and forward across sessions and settings from the titlebar (Cmd/Ctrl+[ and Cmd/Ctrl+]).

This version supports Powers packaged in the open Agent Plugin format and reworks the Agent Focus Mode session rail with pinning, Kiro CLI hand-off, and in-app updates. It also moves Kiro to Code OSS v1.109.5, improves how spec hovers and MCP installs handle untrusted workspace content, and adds bulk session migration and steadier error recovery.

Agent Plugin support for Powers

Install powers aligned with the open Agent Plugin format from a local folder or GitHub URL. Kiro now supports plugins that bundle skills and MCP making powers easier to share across compatible agent tools.

Pin and manage sessions in Agent Focus Mode

Pin a session with Pin Session to keep it at the top of its section. Resume an existing session in Kiro CLI with Open with Kiro CLI. When a new version of Kiro is available, an update row appears in the rail footer, and the settings pane gains a Check for Updates button. Spec documents and task rows in the context panel now open directly in the editor.

Learn more ->

This release introduces tangents: branch into side-conversations that inherit your full conversation history, explore freely, then jump back exactly where you left off. /context also gains a per-tool token breakdown so you can see what's consuming your context window.

/tangent side-conversations (v3)

Need to look something up mid-task without polluting your main thread? /tangent branches into a side-conversation that inherits everything discussed so far — explore freely, then jump back to exactly where you left off. Create named tangents with /tangent , browse your whole conversation tree in a visual picker with /tangent ls, and jump straight back to the main conversation from any depth with /tangent root. Available in V3 mode (kiro-cli --v3).

Learn more ->

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

Guided spec creation (v3)

/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 ->

Plan auto-execution (v3)

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 ->

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.

/upgrade-agent (v3)

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 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.

Introspect Subagent (v3)

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).

Global Hooks (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).

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 ->