Changelog

Kiro Pro Max is a new $100/month tier that fills the gap between Pro+ ($40/month) and Power ($200/month) — for developers who consistently use more than their Pro+ allocation but don't need everything in Power. You get 5,000 credits per month (2.5x Pro+), all premium models, and the full feature set including specs, custom subagents, powers, and hooks. Switch to Pro Max from your account settings, mid-cycle charges are prorated and your new credit allocation takes effect immediately. Try it now ->

This release focuses on portability and getting back to work faster. Export any conversation to share or archive, label terminal windows so you know which session is where, and start a session at the reasoning level you need. Your model and effort choices now stick around on their own, so there's no extra step to make a preference the default.

Save a conversation to share with a teammate, attach to a ticket, or feed into another tool. Run /transcript save to export the full chat as markdown, plaintext, or JSON. The --plain and --json flags also switch the rendered transcript format inline, so you can read it the way you want without leaving the pager. Learn more ->

Keep track of which session is running where. Use /title to set or clear the terminal window title so each window has a meaningful label. Turn it on from /settings display → Terminal title. Learn more ->

Start a session at the reasoning depth the task calls for. The new --effort flag for kiro-cli chat sets the initial effort level (low, medium, high, xhigh, max) when you launch, so quick lookups stay fast and complex work gets the deeper reasoning it needs from the first prompt. Learn more ->

/model and /effort now remember your choices automatically. Switch models or change effort once and Kiro carries that preference into future sessions, so you no longer need to run /model set-current-as-default to make a selection stick. Learn more ->

You can now start a Kiro Web session without connecting a GitHub repo first, and switch to Autonomous mode at any point in a Vibe session, not just at the start. This update also brings relative message timestamps, clearer network mode visibility, and a round of sandbox and reliability fixes.

You no longer need to add a GitHub repository to start a session. Open a session, describe your task, and connect a repo later if you need one.

In a Vibe session, you can now select Autonomous mode after your first prompt, not just at session start. Hand off to the agent whenever you're ready without starting over.

Session messages now show relative timestamps. Hover to see the absolute time, making it easier to track when events occurred during long-running tasks.

Claude Opus 4.8 is now available in the Kiro IDE, CLI, and Web. A direct upgrade from Opus 4.7 with stronger self-verification, more efficient tool calling, and better follow-through on long-horizon projects. Rolling out with experimental support to Pro, Pro+, and Power customers. Ships with a 1M context window, 128K max output, and 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. For the Kiro CLI users to be able to get the best experience out of Opus 4.8, they need to be on Kiro CLI v2.5.0 or above. Learn more ->

This release makes Kiro's work more transparent and more autonomous. Watch the agent reason in real time with thinking display, let subagent pipelines review and revise their own work before handing it back, and control how output renders with new display settings. Message and shell output rendering are also noticeably faster during streaming.

See how the agent works through a problem as it happens. Thinking display streams the model's reasoning in real time, so you can follow its logic, catch a wrong turn early, and understand why it chose an approach. It's enabled by default. Toggle it from /settings > Display > Show thinking - the change applies to your next chat session. Learn more ->

Subagent pipelines can now revise their own work. A reviewer stage can send a task back to the implementer for changes and loop until the work meets the bar, all before results return to you. This turns multi-agent pipelines into self-correcting workflows for cases like code review and refactoring. Learn more ->

Run /settings display to control how Kiro renders output. Toggle streaming animations, decorative ASCII art, and icons versus text-only indicators to match your preference or accessibility needs. Changes take effect immediately, with no restart required. Learn more ->

The daily user activity report now includes a User_Email column containing each user's email address. Enterprise admins no longer need to cross-reference user IDs with a separate directory to identify who generated specific activity. The email appears alongside existing fields like UserId, Subscription_Tier, and Total_Messages in the CSV delivered to your S3 bucket. Learn more ->

Kiro is now included in the AWS HIPAA Eligible Services Reference, meaning organizations subject to the Health Insurance Portability and Accountability Act (HIPAA) can use Kiro as part of their compliant workloads.

Note: This applies to the Kiro IDE and CLI. Kiro Web is not included in HIPAA eligible services at this time.

For details on Kiro's compliance posture, see the Compliance validation documentation.

This release gives you finer control over how conversations flow and how the model thinks. Rewind to any earlier prompt to explore a different path, set reasoning effort per model, and manage all your preferences from one unified settings menu. Workspace initialization is also 88% faster.

Jump back to any earlier prompt in a conversation and continue from that point in a new session. Use /rewind to pick a turn, then branch off without losing your original thread. This is useful when you want to explore an alternative approach or undo a direction the agent took without starting over from scratch. Learn more ->

Control how much thinking the model does with /effort. Choose from five levels: low, medium, high, xhigh, and max. Lower effort means faster, cheaper responses for straightforward tasks; higher effort gives the model more room to reason through complex problems. Learn more ->

Access theme customization, keyboard shortcuts, and terminal configuration from a single /settings command. Run /settings theme to change colors, /settings keybindings to view shortcuts, or /settings terminal to enable Shift+Enter / Option+Enter for multi-line input. The existing /theme command still works as a shortcut. Learn more ->

You can now stop the agent mid-task, see progress while your workspace spins up, and enjoy a more polished layout on smaller screens. This update also resolves several session stability issues.

This release gives you more control over which MCP servers you can connect to, where Kiro lives, and how the TUI responds to your keystrokes.

Connect to HTTP-based MCP servers that don't support Dynamic Client Registration by setting a pre-registered oauth.clientId in your MCP config. This unlocks services like Slack, GitHub, and Figma that require manual app registration for OAuth, so you can use their MCP servers without running your own proxy. Learn more ->

Point Kiro at a different directory for global agents, prompts, skills, steering, settings, and sessions by setting KIRO_HOME before launching. This is handy when you manage dotfiles across machines, keep work and personal profiles separate, or need to isolate Kiro's state for containerized environments. Learn more ->

Remap the cancel, close-menu, and quit actions in the V2 TUI to keys that fit your muscle memory. If Ctrl+C and Esc conflict with your tmux prefix or terminal bindings, you can now pick different keys instead of working around the defaults. Learn more ->

Shell commands the agent runs can now stream output through two additional channels. Write to $AGENT_DISPLAY_OUT to show rich progress in the TUI without bloating the agent's context, and write to $AGENT_CONTEXT_OUT to surface lines in the tool result's agent_notes field. Stdout keeps working as before. Learn more ->