Kiro: baixar versions anteriors

Memory Setting Defaults to Off, Workflow Plan Feedback, and Resilient Powers
This release changes the Memory setting's default to Off, makes approved workflow steps follow your plan feedback, keeps Powers working when a server is unavailable, and fixes several chat, workflow, and MCP issues.
Improvements

Fixes

Memory Setting Defaults to Off, Workflow Plan Feedback, and Resilient Powers
This release changes the Memory setting's default to Off, makes approved workflow steps follow your plan feedback, keeps Powers working when a server is unavailable, and fixes several chat, workflow, and MCP issues.
Improvements

Fixes

Memory Across Chat Sessions
This release brings Memory to every Kiro IDE user. It also makes find more reliable in long Markdown Review documents, fixes a sign-in screen that ignored Cancel, and fixes Kiro failing to start after a .deb install on Ubuntu 24.04.
Carry useful context across sessions with Memory
Memory lets Kiro carry useful context such as repository conventions, corrections, and approaches already ruled out from one session to the next. Select the Memories icon in the activity bar to open the Memory view and review what Kiro remembers. Chat shows when Kiro accesses or changes a memory. Choose how Kiro uses and learns from memories in the Kiro Agent: Memory setting, including Use only, which lets Kiro use memories without changing them. Learn more ->
Improvements

Fixes

Patches

Memory Across Chat Sessions
This release brings Memory to every Kiro IDE user. It also makes find more reliable in long Markdown Review documents, fixes a sign-in screen that ignored Cancel, and fixes Kiro failing to start after a .deb install on Ubuntu 24.04.
Carry useful context across sessions with Memory
Memory lets Kiro carry useful context such as repository conventions, corrections, and approaches already ruled out from one session to the next. Select the Memories icon in the activity bar to open the Memory view and review what Kiro remembers. Chat shows when Kiro accesses or changes a memory. Choose how Kiro uses and learns from memories in the Kiro Agent: Memory setting, including Use only, which lets Kiro use memories without changing them. Learn more ->
Improvements

Fixes

Memory Across Chat Sessions
This release brings Memory to every Kiro IDE user. It also makes find more reliable in long Markdown Review documents, fixes a sign-in screen that ignored Cancel, and fixes Kiro failing to start after a .deb install on Ubuntu 24.04.
Carry useful context across sessions with Memory
Memory lets Kiro carry useful context such as repository conventions, corrections, and approaches already ruled out from one session to the next. Select the Memories icon in the activity bar to open the Memory view and review what Kiro remembers. Chat shows when Kiro accesses or changes a memory. Choose how Kiro uses and learns from memories in the Kiro Agent: Memory setting, including Use only, which lets Kiro use memories without changing them. Learn more ->
Improvements

Fixes

Markdown Review, What's New Announcements, and Workflow Step Notifications
This release brings Markdown Review to every Kiro IDE user, so you can comment on Markdown files in your workspace and send the comments to Kiro in one batch. It also adds a What's new announcement browser, makes workflow step notifications easier to scan, can generate commit messages before you stage changes, and fixes terminal, workflow, and sign-in issues.
Review Markdown documents
Open a .md file in your workspace in a rendered review panel, comment on exact passages, and send your comments together. The panel stays current as the file changes and adds an outline, Mermaid controls, and horizontal scrolling for wide tables. Open it from the editor title bar, Command Palette, Specs view, or the Review button on supported spec documents. Learn more ->
Improvements

Fixes

Local Command Sandbox, Start Saved Workflows from Chat, and Live Tab Status
Limit what agent-run shell commands can reach, start saved Workflows from chat, and see live session status on editor tabs.
This release lets you limit what agent-run shell commands can reach and start saved Workflows from chat. It also shows live session status on editor tabs, explains model fallbacks, loads MCP tools on demand, and fixes Workflow, chat, and account issues.
Contain agent-run shell commands in a sandbox
Turn on the local command sandbox to limit what agent-run shell commands and their child processes can access. Choose whether outbound network access is blocked, limited to common development hosts, or open. You can also run local stdio MCP servers inside the same sandbox.
The agent, built-in file tools, and remote MCP servers stay outside the sandbox. Permission rules still govern agent actions. The sandbox reduces risk but cannot guarantee complete isolation, so keep reviewing proposed commands. Select Command sandbox in the status bar to open the settings and confirm the sandbox is active. Learn more ->
Start saved Workflows from chat
Type /workflow-run, choose a recipe, complete its inputs, and start the run. Kiro opens Workflows on the new run. Learn more ->
Improvements

Fixes

Workflow Feedback, Power Search, and Flexible Hook Matching
This release adds a feedback link for Workflows, fixes several chat, terminal, and source control issues, and improves workflow reliability, spec-only commands, and Hook matching.
Improvements

Fixes

Workflows, Safer Untrusted Workspaces, and Enterprise Sign-In Controls
Run reusable multi-agent Workflows in the background, apply stronger safeguards to Kiro configuration, and manage enterprise sign-in options.
IDE 1.2 introduces Workflows, strengthens safeguards for untrusted workspaces, and adds enterprise controls for sign-in methods. This release also reworks session details, keeps enterprise traffic in your profile's Region, and fixes authentication, debugging, and reliability issues.
Run multi-agent Workflows in the background
Ask Kiro to run a reusable, multi-step plan while you continue in the parent chat. Each step runs in its own agent session. Use the Workflows area above the chat to inspect progress, open a step, and pause, resume, or stop the run. Workflows are off by default: turn on Workflows in Workspace Configuration in Agent Focus, or set kiroAgent.workflows.enabled in Settings, then start a new chat session. Learn more ->
Protect Kiro configuration and Workflow recipes
Kiro asks before the agent changes agent, Hook, or Power files, or the Workflow recipes in .kiro/workflows/ that define your Workflows, even when broader file permissions allow the write. In an untrusted workspace, Kiro also asks before changing any other Kiro configuration and before each command runs, even when you previously allowed it. Workflow recipes in an untrusted workspace are not loaded until you trust the workspace. Learn more ->
Improvements

Fixes

Patches

Workflows, Safer Untrusted Workspaces, and Enterprise Sign-In Controls
Run reusable multi-agent Workflows in the background, apply stronger safeguards to Kiro configuration, and manage enterprise sign-in options.
IDE 1.2 introduces Workflows, strengthens safeguards for untrusted workspaces, and adds enterprise controls for sign-in methods. This release also reworks session details, keeps enterprise traffic in your profile's Region, and fixes authentication, debugging, and reliability issues.
Run multi-agent Workflows in the background
Ask Kiro to run a reusable, multi-step plan while you continue in the parent chat. Each step runs in its own agent session. Use the Workflows area above the chat to inspect progress, open a step, and pause, resume, or stop the run. Workflows are off by default: turn on Workflows in Workspace Configuration in Agent Focus, or set kiroAgent.workflows.enabled in Settings, then start a new chat session. Learn more ->
Protect Kiro configuration and Workflow recipes
Kiro asks before the agent changes agent, Hook, or Power files, or the Workflow recipes in .kiro/workflows/ that define your Workflows, even when broader file permissions allow the write. In an untrusted workspace, Kiro also asks before changing any other Kiro configuration and before each command runs, even when you previously allowed it. Workflow recipes in an untrusted workspace are not loaded until you trust the workspace. Learn more ->
Improvements

Fixes

Configurable Terminal Timeouts, Clickable File Links, and Agent Focus Session Restore
IDE 1.1.70 lets you set a default timeout for local agent commands, opens Markdown links to workspace files in the editor, and keeps Agent Focus file and folder context aligned with the active project. Restored Agent Focus sessions now reconnect without leaving a blank chat pane. Background process output cards show their results, Markdown tables keep their styling, and Mermaid diagrams no longer leave stray error graphics while streaming.
Improvements

Fixes

Agent Artifacts and Native ARM64 Builds
IDE 1.1 lets agents produce durable artifacts you can review and return to, adds native ARM64 builds for Windows and Linux, and updates the editor foundation to Code OSS 1.131. Compacted conversations retain the right context, MCP failures are clearer, Hooks are more reliable, and enterprise profiles route requests to the selected region.
Review agent-created artifacts
Kiro can turn documents, diagrams, code, images, and other agent outputs into durable artifacts instead of leaving them buried in the chat transcript. Open a compact preview from the conversation, review the full artifact beside the chat in Agent Focus, or return to it from the Agent Focus context panel. Learn more ->
Install Kiro natively on ARM64
Install native ARM64 builds for Windows and Linux instead of relying on x64 emulation. Choose the ARM64 download for your platform from the Kiro downloads page.
Recent IDE 1.0 highlights
These capabilities shipped earlier in the IDE 1.0 release line and are included here for context.
- Cloud Configuration and synced Powers (1.0.437): Access supported personal configuration across IDE surfaces and try cloud-synced Powers from the installed list. Release notes ->
- Permission improvements and configured Windows shells (1.0.337): Keep ignored files out of search, apply filesystem and command permission rules more accurately, and run agent commands in your configured Windows terminal profile. Release notes ->
- Cloud Sessions and Agent Focus upgrades (1.0.293): Start Cloud Sessions from Agent Focus, collapse the session rail for more chat space, answer attention cards in place, and move back or forward between views. Release notes ->
- Agent Plugin support and session pinning (1.0.288): Use Agent Plugins through Powers and pin important Agent Focus sessions. Release notes ->
Improvements

Fixes

Cloud Configuration, Synced Powers, and Agent Focus Reliability
With Cloud configuration enabled, your supported personal configuration appears across the IDE and Agent Focus, and cloud-synced Powers are ready to try from the installed list. This version also keeps in-progress cloud-session drafts available across navigation and preserves the welcome view until you send your first prompt.
Use Cloud configuration across the IDE
When Cloud configuration is enabled for your account, access personal Steering, custom agents, Skills, Powers, and Hooks from their usual IDE surfaces. Cloud indicators identify items managed in Kiro Web. Steering, Skills, and Hooks open as read-only previews with an Edit in web action, and Agent Focus shows the same source and management links. Learn more ->
Try cloud-synced Powers in the IDE
Cloud-synced Powers now appear in the installed Powers list, where you can select Try power and review their bundled Skills and MCP configuration. Manage these account-backed Powers in Kiro Web. Learn more ->
Fixes

Third-Party Extension Compatibility and More Reliable MCP Sign-In
This version lets third-party extensions work alongside Kiro, adds support for the latest MCP protocol revision with more reliable sign-in, reduces extension host crashes during large agent responses, and keeps agent turns going when the network briefly drops.
Improvements

Fixes

Third-Party Extension Compatibility and More Reliable MCP Sign-In
This version lets third-party extensions work alongside Kiro, adds support for the latest MCP protocol revision with more reliable sign-in, reduces extension host crashes during large agent responses, and keeps agent turns going when the network briefly drops.
Improvements

Fixes

Permission Improvements and Configured Windows Shells
This version keeps ignored files out of search results, improves filesystem and command permission rules, and runs agent commands in your configured terminal profile on Windows.
Improvements

Nested AGENTS.md and Long-Session Efficiency
Add AGENTS.md files throughout your workspace to give Kiro instructions scoped to each directory tree. This version also lowers idle resource use, preserves more context in long sessions, and improves Cloud configuration, chat, hooks, and MCP connections.
Improvements

Fixes

Cloud Sessions and Agent Focus Mode Upgrades
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. Learn more ->
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+]). Learn more ->
Improvements

Fixes

Agent Plugin Support and Session Pinning
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 packaged in the open Agent Plugin format from a local folder or GitHub URL. Kiro includes the plugin's bundled skills, steering, scripts, and assets, making Powers easier to share across compatible agent tools. Learn more ->
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 ->
Improvements

Fixes

Editor Actions, Guided Hook Creation, and Code OSS Upgrade
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.
Improvements

Fixes

Global Hooks, Session Search, and Reliability Fixes
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.
Improvements

Fixes

Global Hooks, Session Search, and Reliability Fixes
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.
Improvements

Fixes

Global Hooks, Session Search, and Reliability Fixes
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.
Improvements

Fixes

Faster Sessions, Compaction Fixes, and PowerShell Trust
Note: To get the latest 1.0.x release, download it directly from kiro.dev/downloads. Auto-updates are being rolled out gradually to users.
This release delivers faster session startup, fixes the compaction loop that caused repeated Context limit exceeded errors on large sessions, and adds full PowerShell trust support on Windows. MCP tools now also recover from transient network failures instead of failing silently.
Improvements

Fixes

Global Hooks, Session Search, and Reliability Fixes
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.
Improvements

Fixes

Faster Sessions, Compaction Fixes, and PowerShell Trust
Note: To get the latest 1.0.x release, download it directly from kiro.dev/downloads. Auto-updates are being rolled out gradually to users.
This release delivers faster session startup, fixes the compaction loop that caused repeated Context limit exceeded errors on large sessions, and adds full PowerShell trust support on Windows. MCP tools now also recover from transient network failures instead of failing silently.
Improvements
- Faster session startup and shell commands: Permission checks are now significantly faster, especially for sessions with many saved trust rules. Sessions start quicker and each shell command runs with less overhead before execution
- MCP tool resilience: MCP tools and profile lookups now recover gracefully from transient network failures. A brief connectivity interruption no longer permanently disables tools for the rest of the session
- PowerShell command trust: Always allow rules now work correctly for piped and compound PowerShell commands on Windows. Previously, PowerShell substitutions ($(...)) were opaque to the trust system and re-prompted indefinitely
- Per-agent hooks: Inline hooks declared on custom agent profiles now register and fire correctly. Previously they were silently dropped
- Copy Request IDs — A new Copy Request ID(s) option in the message copy menu lets you grab backend request IDs from any turn for support tickets
Fixes
- Fixed context compaction loop where summarization couldn't shrink sessions containing a single large turn, causing repeated Context limit exceeded errors
- Fixed the first user prompt steering the agent's behavior after context compaction, causing it to forget the current task and repeat early instructions
- Fixed supervised mode silently reverting accepted same-file edits when the agent made multiple edits to one file in a single turn
- Fixed agent hang when a sub-agent asks a free-form question with no predefined options, and added a text input UI so users can answer these questions
- Fixed older sessions failing every turn with a validation error after tool names changed between versions. These sessions now self-heal on load
- Fixed shell type detection on Windows defaulting to cmd even when running PowerShell, which prevented the PowerShell trust parser from being used
- Fixed Agent Focus context panel auto-opening for specs the session only read rather than authored
- Fixed the feedback form not rendering above the chat webview in Agent Focus mode
- Fixed the Settings pane in Agent Focus being kicked back to chat after a few seconds
- Fixed turns appearing blank when the model declines a request due to content policy. A clear refusal message now appears instead

Hooks on Agent Writes, Lazy MCP Auth, and Multi-Window Sync
This release re-enables auto-updates and brings hooks to agent-driven file changes, automatic OAuth for MCP servers that require sign-in, multi-window settings sync, and several trust and connectivity fixes.
Improvements
- Hooks fire on agent file writes: Hooks now trigger when the agent writes, creates, or deletes files not just on manual saves. Your format-on-save and review-on-create hooks apply to agent-driven changes automatically
- Lazy authentication for MCP servers: MCP servers that challenge with HTTP 401 on tool calls now trigger an OAuth flow automatically. Tools that require sign-in work without manual re-authentication
- Multi-window sync: Config and mode changes (autopilot/supervised, model, effort level) now sync to all windows viewing the same session
- Supervised mode approval redesign: Approval controls match autopilot's layout (Accept left, Reject right). The file list is scrollable with improved tooltips on file names
- Agent Focus Mode polish: Delete session skips the confirmation dialog; menus dismiss on Escape; file picker (Cmd+P) blocked in AFM window
- Policy-configurable update URL (Enterprise): Admins can now set a custom update endpoint via policy, allowing organizations to stage and control which Kiro versions their teams receive
- Profile error messages (Enterprise): Clearer error messages when admin-restricted users have no profile access
Fixes

Session Restore, Performance Optimizations, and Custom Agent Enhancements
Note: To get the latest 1.0.x release (1.0.89 or later), download it directly from kiro.dev/downloads. Auto-updates are paused at this time and we are working on re-enabling them.
This release brings performance improvements and Agent Focus Mode polish. Sessions restore automatically on launch, idle resource consumption is lower, prepaid credit packs appear in the account dashboard, and several fixes ensure permissions, hooks, and steering behave correctly across windows and custom agent profiles.
Improvements
- Agent Focus session restore: Kiro restores your last active Agent Focus Mode session when you reopen the IDE, so you pick up where you left off without manually reopening a session
- Rename Agent Focus sessions: Rename sessions directly from the session rail for better organization
- Lower idle CPU usage: Telemetry, battery monitoring, and status bar updates are optimized to reduce background resource consumption when Kiro is idle.
- Faster permissions evaluation: Permission checks run faster for users with many allow/deny rules
- More accurate context usage: Context usage percentage now reflects your model's actual window size rather than a fixed estimate
- Prepaid credits visible in the IDE: Organization prepaid credit packs now appear in the Account Dashboard with remaining balance and expiration, so you can track consumption without leaving Kiro
- Triggered hooks visible in chat: When a hook fires, its name appears in the tool-call collapser so you can see which hook ran and why
- Custom agent commands update live: Adding or modifying agent profiles in .kiro/agents/ immediately updates the agent selector in chat. No restart needed
- Mode descriptions in picker: Agent modes now show their description in the mode selector, making it easier to pick the right mode
- Spec tasks respect model choice: Spec workflow tasks now use the model you selected rather than defaulting to a fixed model
- Richer terminal output in chat: Terminal content is embedded as a structured block in chat, improving readability for multi-line command results
- Run Command reliability: The standalone Run Command action no longer completes prematurely for commands with buffered output.
- Paginated MCP List calls: The MCP client now paginates List calls, supporting servers that expose many resources or tools without hitting size limits
- Policy bundles in agent profiles: Reference built-in permission presets like read-shell, edit-workspace, or dev-shell from your agent profiles, so you don't have to write individual rules from scratch
- Safer trust migration: File read/write grants from legacy permission formats are no longer auto-migrated. These are covered by the edit-workspace preset instead, preventing overly broad inherited rules
- Thinking mode defaults: Models that support extended thinking no longer have it forced on by default. Your model and effort selection is respected as-is
Fixes

Parallel Task Execution, Quick Plan, and Requirements Analysis
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.
Parallel Task Execution
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 ->
Quick Plan
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 ->
Analyze Requirements
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 ->
Improvements
- Command palette - Restored standard VS Code positioning with drag-and-drop support via the title bar
- Kiro Light theme - Status bar items no longer show a dark grey background
- Sync Files - Renamed the Update tasks button in tasks.md to Sync Files
- Extension host crash recovery - Transient failures now restart automatically. Repeated crashes show a "Restart Kiro" action with clear guidance
Fixes
- Fixed source control panel showing "no folders containing Git" after extension host isolation
- Fixed Generate Commit Message and branch detection with the dedicated extension host
- Fixed missing per-turn approval snackbar in supervised mode
- Fixed unexpected positioning for command palette after upgrading from previous versions
Patches

Parallel Task Execution, Quick Plan, and Requirements Analysis
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.
Parallel Task Execution
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 ->
Quick Plan
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 ->
Analyze Requirements
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 ->
Improvements
- Command palette - Restored standard VS Code positioning with drag-and-drop support via the title bar
- Kiro Light theme - Status bar items no longer show a dark grey background
- Sync Files - Renamed the Update tasks button in tasks.md to Sync Files
- Extension host crash recovery - Transient failures now restart automatically. Repeated crashes show a "Restart Kiro" action with clear guidance
Fixes

Patches

Parallel Task Execution, Quick Plan, and Requirements Analysis
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.
Parallel Task Execution
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 ->
Quick Plan
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 ->
Analyze Requirements
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 ->
Improvements
- Command palette - Restored standard VS Code positioning with drag-and-drop support via the title bar
- Kiro Light theme - Status bar items no longer show a dark grey background
- Sync Files - Renamed the Update tasks button in tasks.md to Sync Files
- Extension host crash recovery - Transient failures now restart automatically. Repeated crashes show a "Restart Kiro" action with clear guidance
Fixes

Patches

Parallel Task Execution, Quick Plan, and Requirements Analysis
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.
Parallel Task Execution
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 ->
Quick Plan
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 ->
Analyze Requirements
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 ->
Improvements
- Command palette - Restored standard VS Code positioning with drag-and-drop support via the title bar
- Kiro Light theme - Status bar items no longer show a dark grey background
- Sync Files - Renamed the Update tasks button in tasks.md to Sync Files
- Extension host crash recovery - Transient failures now restart automatically. Repeated crashes show a "Restart Kiro" action with clear guidance
Fixes
- Fixed source control panel showing "no folders containing Git" after extension host isolation
- Fixed Generate Commit Message and branch detection with the dedicated extension host
- Fixed missing per-turn approval snackbar in supervised mode
- Fixed unexpected positioning for command palette after upgrading from previous versions
Patches

Parallel Task Execution, Quick Plan, and Requirements Analysis
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.
Parallel Task Execution
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 ->
Quick Plan
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 ->
Analyze Requirements
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 ->
Improvements
- Command palette - Restored standard VS Code positioning with drag-and-drop support via the title bar
- Kiro Light theme - Status bar items no longer show a dark grey background
- Sync Files - Renamed the Update tasks button in tasks.md to Sync Files
- Extension host crash recovery - Transient failures now restart automatically. Repeated crashes show a "Restart Kiro" action with clear guidance
Fixes

Patches

Parallel Task Execution, Quick Plan, and Requirements Analysis
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.
Parallel Task Execution
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 ->
Quick Plan
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 ->
Analyze Requirements
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 ->
Improvements
- Command palette - Restored standard VS Code positioning with drag-and-drop support via the title bar
- Kiro Light theme - Status bar items no longer show a dark grey background
- Sync Files - Renamed the Update tasks button in tasks.md to Sync Files
- Extension host crash recovery - Transient failures now restart automatically. Repeated crashes show a "Restart Kiro" action with clear guidance
Fixes

Patches

Parallel Task Execution, Quick Plan, and Requirements Analysis
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.
Parallel Task Execution
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 ->
Quick Plan
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 ->
Analyze Requirements
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 ->
Improvements
- Command palette - Restored standard VS Code positioning with drag-and-drop support via the title bar
- Kiro Light theme - Status bar items no longer show a dark grey background
- Sync Files - Renamed the Update tasks button in tasks.md to Sync Files
- Extension host crash recovery - Transient failures now restart automatically. Repeated crashes show a "Restart Kiro" action with clear guidance
Fixes

Patches

Parallel Task Execution, Quick Plan, and Requirements Analysis
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.
Parallel Task Execution
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 ->
Quick Plan
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 ->
Analyze Requirements
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 ->
Improvements
- Command palette - Restored standard VS Code positioning with drag-and-drop support via the title bar
- Kiro Light theme - Status bar items no longer show a dark grey background
- Sync Files - Renamed the Update tasks button in tasks.md to Sync Files
- Extension host crash recovery - Transient failures now restart automatically. Repeated crashes show a "Restart Kiro" action with clear guidance
Fixes
- Fixed source control panel showing "no folders containing Git" after extension host isolation
- Fixed Generate Commit Message and branch detection with the dedicated extension host
- Fixed missing per-turn approval snackbar in supervised mode
- Fixed unexpected positioning for command palette after upgrading from previous versions
Patches

Parallel Task Execution, Quick Plan, and Requirements Analysis
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.
Parallel Task Execution
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 ->
Quick Plan
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 ->
Analyze Requirements
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 ->
Improvements
- Command palette - Restored standard VS Code positioning with drag-and-drop support via the title bar
- Kiro Light theme - Status bar items no longer show a dark grey background
- Sync Files - Renamed the Update tasks button in tasks.md to Sync Files
- Extension host crash recovery - Transient failures now restart automatically. Repeated crashes show a "Restart Kiro" action with clear guidance
Fixes

Patches

Parallel Task Execution, Quick Plan, and Requirements Analysis
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.
Parallel Task Execution
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 ->
Quick Plan
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 ->
Analyze Requirements
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 ->
Improvements
- Command palette - Restored standard VS Code positioning with drag-and-drop support via the title bar
- Kiro Light theme - Status bar items no longer show a dark grey background
- Sync Files - Renamed the Update tasks button in tasks.md to Sync Files
- Extension host crash recovery - Transient failures now restart automatically. Repeated crashes show a "Restart Kiro" action with clear guidance
Fixes
- Fixed source control panel showing "no folders containing Git" after extension host isolation
- Fixed Generate Commit Message and branch detection with the dedicated extension host
- Fixed missing per-turn approval snackbar in supervised mode
- Fixed unexpected positioning for command palette after upgrading from previous versions

This release adds policy-driven configuration for private extension registries and several bug fixes.
Improvements

- Enterprise extension registry: Administrators can configure a private extension registry through OS-level policy (MDM, Group Policy, or policy file) without modifying the application bundle
Bug fixes

- Fixed chat panel turning grey and unresponsive when editing large files (~5,000+ lines)
- Fixed Source Control panel showing "no folders containing Git" and Generate Commit Message not working
- Fixed enterprise (IAM Identity Center) users intermittently seeing "No model available" when MCP configuration is managed by organization policy
- Fixed repeated "Unable to fetch account usage data" error toasts
- Disabled experimental WebGPU to mitigate CVE-2026-5281

MCP Registry Governance, Model Governance, and Document Attachments
This release gives enterprise teams centralized control over MCP server access and model availability, and adds document attachment support to chat.
MCP Registry Governance

Enterprise administrators using IAM Identity Center can now control which MCP servers their organization is allowed to use. Create a JSON registry file listing approved servers, host it over HTTPS, and configure the URL in the Kiro console. The registry supports remote (HTTP) and local (stdio) servers across npm, PyPI, and OCI package types, with ${VAR} placeholders for user-specific values like auth tokens. Kiro syncs with the registry every 24 hours, enforces version-pinned access, and works alongside the existing MCP on/off toggle to give you full control at the org or account level.
Model Governance

Enterprise administrators can now control which AI models are available to users in their organization. Toggle on model access management in the Kiro console under Settings > Shared settings > Model availability, then curate an approved list of models. You can also set a default model that auto-applies across all clients. This is especially relevant for data residency requirements — experimental models using global cross-region inference can be removed from the approved list until they move to GA with regional inference. Once enabled, only approved models appear in the model selector across both the IDE and CLI.
Document Attachments
You can now attach documents directly to chat messages by pasting or dragging files into the input. Supported formats include PDF, CSV, DOC, DOCX, XLS, XLSX, HTML, TXT, and Markdown. Documents are sent to the model as native document blocks, so the agent can read and reason over their contents. You can attach up to 5 documents per message and mix them with text and images in the same prompt.
Improvements
- Subagent context: Subagents now receive richer context from parent sessions, including file tree structure, for more accurate responses
- Chat performance: Reduced re-renders and improved responsiveness in large chat sessions
- Session storage cleanup: Least-recently-modified sessions are automatically evicted when storage exceeds 500 MB
- Streaming animation: Agent responses render with a smoother streaming animation
- Rename symbol: The rename symbol tool now supports accept/reject in supervised mode, consistent with other file-modifying tools
- Code editing accuracy: Improved how the agent targets and modifies code, with better accuracy for Java and fewer misplaced edits
- Web fetch rendered mode: A new rendered fetch mode uses a browser engine to extract content from JavaScript-heavy pages that return empty results with standard fetching
- Web fetch: Web fetch now supports `text/plain` content type responses.
- MCP connection sharing: MCP server connections are now shared across chat sessions instead of created per session, reducing resource usage
- In-chat search: Search within chat conversations using Cmd+F (Ctrl+F on Windows/Linux)
- Protected file approval: Kiro now prompts for confirmation before modifying sensitive workspace files like mcp.json, .kiroignore, .vscode/ settings, .git/, and .code-workspace files, regardless of autonomy mode
- Support link: Updated the IDE support link to point to the new support form
Fixes

Patches

- Fixed agent chat getting stuck in "Working" state during parallel tool calls
- Fixed spec tasks not having access to Powers, MCP servers, and skills
- Fixed MCP streaming commands failing for enterprise users
- Fixed sign-in failures caused by missing profile data across API calls
- Fixed social login users being unable to recover when profile data was empty
- Fixed enterprise telemetry incorrectly showing content collection as enabled for IdC and external IdP users

This release adds 2 new slash commands that streamline the spec workflow, improves Linux compatibility, and resolves several issues affecting Windows and remote SSH users.
Improvements

- /quick-spec slash command: Type /quick-spec followed by a description to generate all three spec documents (requirements, design, tasks) in one shot. After generation, you can iterate conversationally to refine all documents at once
- /architecture-selection slash command: Invoke /architecture-selection to run a systematic architecture analysis between the requirements and design phases. Produces 2-3 candidate architectures with metrics, selects the best fit, and feeds the result into design generation.
- Spec testing guidance — The spec workflow now intelligently skips property-based testing for scenarios where it doesn't apply, such as IaC templates, UI components, and simple CRUD operations, and recommends appropriate alternatives instead
- Linux compatibility: Lowered the glibc requirement to 2.28+, expanding support to RHEL 8+ and Ubuntu 20.04+
- Command working directory: Command chat cards now display the working directory next to the command label, so you can tell where a command is running
Fixes

- Fixed autocomplete showing error toasts for unsupported file types
- Fixed login failures when using Kiro over remote SSH connections
- Fixed the # context provider dropdown closing immediately when triggered after a previously inserted mention node
- Fixed the Spec "Continue" button injecting extra text into the chat message
- Fixed a path validation issue on Windows
- Fixed long-running terminal commands being incorrectly terminated due to execution timeout on Windows
- Fixed subscription API calls missing profile information, which could cause issues with plan management
- Fixed drag-and-drop from the file explorer not working on Windows
- Fixed context provider submenu showing the top-level providers list instead of the expected submenu items

Fixed agent hanging indefinitely in supervised mode when a write tool fails

This patch adds the ability to close a chat tab with shortcuts, shows MCP server names in tool approval, and fixes a checkpoint restore bug that could delete files.
Improvements

- Close chat tab: Press Cmd+W (Ctrl+W on Windows/Linux) to close the active chat tab
- MCP tool approval: The tool approval dialog now shows the MCP server name next to the tool name (e.g., slack-server / send_slack_message), so you can tell which server is requesting access
- MCP registry errors: Registry servers that can't be resolved now appear as error nodes in the MCP panel instead of silently failing
- Copy button: Updated the copy button icon for visual consistency
Fixes

- Fixed checkpoint restore deleting files that existed before the agent session. Only files created by the agent are now removed on restore
- Fixed the agent being able to create .git pointer files, preventing a potential code execution risk through Git hooks
- Fixed Cmd+Shift+Enter shortcut for trusting commands not responding when a diff editor was open
- Fixed login failures for users behind corporate proxies where profile discovery attempted to reach unavailable regional endpoints
- Fixed the MCP panel showing server entries when MCP was disabled in enterprise settings
- Fixed the spec explorer not showing the bugfix document for bugfix-type specs

Fixed agent hanging indefinitely in supervised mode when a write tool fails

MCP Registry Governance, Model Governance, and Document Attachments
This release gives enterprise teams centralized control over MCP server access and model availability, and adds document attachment support to chat.
MCP Registry Governance
Enterprise administrators using IAM Identity Center can now control which MCP servers their organization is allowed to use. Create a JSON registry file listing approved servers, host it over HTTPS, and configure the URL in the Kiro console. The registry supports remote (HTTP) and local (stdio) servers across npm, PyPI, and OCI package types, with ${VAR} placeholders for user-specific values like auth tokens. Kiro syncs with the registry every 24 hours, enforces version-pinned access, and works alongside the existing MCP on/off toggle to give you full control at the org or account level.
Model Governance
Enterprise administrators can now control which AI models are available to users in their organization. Toggle on model access management in the Kiro console under Settings > Shared settings > Model availability, then curate an approved list of models. You can also set a default model that auto-applies across all clients. This is especially relevant for data residency requirements — experimental models using global cross-region inference can be removed from the approved list until they move to GA with regional inference. Once enabled, only approved models appear in the model selector across both the IDE and CLI.
Document Attachments
You can now attach documents directly to chat messages by pasting or dragging files into the input. Supported formats include PDF, CSV, DOC, DOCX, XLS, XLSX, HTML, TXT, and Markdown. Documents are sent to the model as native document blocks, so the agent can read and reason over their contents. You can attach up to 5 documents per message and mix them with text and images in the same prompt.
Improvements
- Subagent context: Subagents now receive richer context from parent sessions, including file tree structure, for more accurate responses
- Chat performance: Reduced re-renders and improved responsiveness in large chat sessions
- Session storage cleanup: Least-recently-modified sessions are automatically evicted when storage exceeds 500 MB
- Streaming animation: Agent responses render with a smoother streaming animation
- Rename symbol: The rename symbol tool now supports accept/reject in supervised mode, consistent with other file-modifying tools
- Code editing accuracy: Improved how the agent targets and modifies code, with better accuracy for Java and fewer misplaced edits
- Web fetch rendered mode: A new rendered fetch mode uses a browser engine to extract content from JavaScript-heavy pages that return empty results with standard fetching
- Web fetch: Web fetch now supports `text/plain` content type responses.
- MCP connection sharing: MCP server connections are now shared across chat sessions instead of created per session, reducing resource usage
- In-chat search: Search within chat conversations using Cmd+F (Ctrl+F on Windows/Linux)
- Kiro Powers progress: Power operations now appear in the execution snackbar so you can track their progress
- Protected file approval: Kiro now prompts for confirmation before modifying sensitive workspace files like mcp.json, .kiroignore, .vscode/ settings, .git/, and .code-workspace files, regardless of autonomy mode
- Support link: Updated the IDE support link to point to the new support form
Fixes
- Fixed duplicate agent messages appearing when multiple chat sessions were open simultaneously
- Fixed chat input text being lost when navigating to History and back
- Fixed hook command execution approval not working properly for multi-line shell commands
- Fixed spec generation latency increasing due to subagents
- Fixed a token refresh loop that could cause repeated login prompts
- Fixed prompt text being lost when navigating through history or switching sessions
- Fixed markdown re-render performance and overly broad URI m

This patch adds a context usage banner and fixes chat reliability issues including session history loss, supervised mode and more.
Improvements
- Context usage: Kiro now shows a breakdown of context usage so you can see what's consuming your model's context window. A warning appears when any single category (such as MCP tools or steering files) exceeds 30% of available context. The estimate is model-aware and updates in real time as MCP servers connect.
- Terminal focus control: The terminal panel no longer steals focus when the agent runs commands
Fixes
- Fixed session history loss on window reload and when closing multiple windows
- Applied a critical Chromium security patch (CVE-2026-2441)
- Fixed a race condition with supervised mode silently falling back to autopilot
- Fixed the spec explorer not refreshing when a new spec is created
- Fixed the show terminal option for long-running processes
- Standardized bugfix spec documents terminology (Fault Condition --> Bug Condition)
- Fixed subagents skipping spec tasks or marking them complete prematurely
- Fixed context selection shortcuts. Cmd+Shift+L (Ctrl+Shift+L on Windows/Linux) now correctly adds selected content to a new session, while Cmd+L (Ctrl+L) adds it to the active chat.

Fixed an issue where the agent could not write or modify files during spec and task execution

New Spec Workflows, Hunk-Based Edits, Task Hooks, and MCP Prompts
This release introduces new spec workflows that let you design features architecture-first and fix bugs with structured root cause analysis. Supervised mode now lets you review changes at the hunk level for precise control. New hook triggers automate work around spec tasks, and MCP servers can now surface prompts, templates, and elicitation support directly in chat.
Design-First Feature Specs
A new Design-First workflow lets you start a feature spec from technical architecture instead of requirements. Provide a high-level or low-level design, pseudocode, or system diagram and Kiro derives feasible requirements from it. This is ideal when you have strict non-functional constraints, an existing design to port, or want to think through the architecture before defining user-facing behavior. Learn more ->
Bugfix Specs
Specs now include a dedicated Bugfix workflow. Describe the issue you're seeing and Kiro walks you through root cause analysis, fix design, and regression prevention. The result is a `bugfix.md` that captures current behavior, expected behavior, and what must remain unchanged, giving the agent clear guardrails before it writes a single line of code. Learn more ->
Hunk-Based Review in Supervised Mode
Supervised mode now presents file changes as individual hunks instead of full-file diffs. Each hunk is a logical group of related lines that you can independently accept, reject, or discuss with inline chat. You can also accept changes at the file level or accept all changes at once. This gives you precise control over exactly which parts of a change to keep. Learn more ->
Pre and Post Task Execution Hooks
Two new hook triggers let you automate work around spec task execution. Pre Task Execution fires before a task begins, so you can run setup scripts or validate prerequisites. Post Task Execution fires after a task completes, letting you run tests, linting, or notify external systems automatically. Combine these with the existing hook actions to build end-to-end automation around your spec workflows. Learn more ->
MCP Prompts, Resource Templates, and Elicitation
MCP servers can now provide prompts and resource templates that appear in the context provider (#) menu in chat. Select a prompt to insert pre-built instructions, or fill in a resource template's parameters to pull in specific content as context. During tool execution, servers can also request additional input from you through elicitation. Kiro supports elicitation so servers can request the information they need without interrupting your workflow. Learn more ->
Improvements
- Skills and steering: Skills and auto-included steering files can now be activated from slash commands in chat
- Conversation export: Sub-agent executions are now included when exporting a conversation
- Hook creation UI: New Save and Clear buttons in the hook creation form, plus manual hook creation flow and recursive folder expansion for hook detection
- Hook panel: Delete hooks directly from the context menu in the hooks explorer
- Hook time limits: runCommand hooks now support configurable time limits
- Terminal input detection: Kiro detects when a terminal command is waiting for user input and shows a warning in the UI
- Code tool: Improved syntax validation, auto-repair, and tighter fuzzy matching for more reliable code edits
- Spec continue button: A continue button in the spec navbar lets you advance through spec phases without switching context
- Spec preview: Floating preview button overlay for markdown spec files
- Web fetch: Improved content-type handling for broader compatibility with fetched pages.
- Markdown rendering: Improved markdown streaming in chat
Fixes
- Inline chat and manual edits made during supervised review are now always saved
- Fixed spec document generation prompt and continue button losing conversation history context
- Fixed PreToolUse and PostToolUse hooks not firing
- Fixed hook creation not r

External Identity Provider Support for Kiro IDE
This release adds support for signing in to Kiro IDE with Okta or Microsoft Entra ID credentials.
Enterprise SSO with Okta and Entra ID
Video unavailable
Enterprise teams can now connect Okta or Microsoft Entra ID alongside AWS IAM Identity Center, giving organizations flexibility in how they manage user access. Developers sign in to the IDE with their existing corporate credentials. User and group synchronization happens automatically through SCIM provisioning. Configure your IdP once and it works across both Kiro IDE and CLI. Learn more ->

Includes 0.8.86 patch.

This release introduces web tools for searching and fetching content from the internet, enhanced hooks with new action types, subagents for parallel task execution, and improved supervised mode with per-file review capabilities.
Web tools
Kiro can now search the web and fetch content from URLs directly in chat. Use web tools to look up current documentation, find the latest library versions, or research solutions to technical problems. This keeps your development workflow in one place without switching to a browser.
Contextual hooks
Introducing contextual hooks with two new triggers: Prompt Submit and Agent Stop. These hooks fire at key moments in the agent workflow, letting you inject context or run commands before the agent acts. Choose between Agent Prompt actions to instruct the agent with natural language, or Shell Command actions to run commands locally without consuming credits.
Subagents
Introducing subagents for parallel task execution. Kiro can now run multiple tasks simultaneously or delegate to specialized subagents. Two built-in subagents are available: a context gatherer for exploring projects and a general-purpose agent for parallelizing tasks. Each subagent has its own context window, keeping the main agent context clean. Use subagents to investigate multiple data sources in parallel, analyze GitHub issues across repositories, or extend your context window limits without requiring summarization.
Enhanced Supervised Mode
Supervised mode now offers granular control over code changes with per-file review capabilities. When Kiro makes changes to multiple files, you can review each file individually and selectively accept or reject changes. This turn-based approach works in both vibe chat and spec chat sessions, giving you full visibility into each modification.
Improvements (7)
- Terminal - Improved git pager handling to prevent terminal hangs
- Enterprise auth - Smoother sign-in with cached enterprise auth startURL
- .kiroignore support - Exclude specific files from agent access using gitignore syntax. Create `.kiroignore` in your project root with patterns for files to skip, then add it to the `agentIgnoreFiles` setting
- Context Usage - See context window usage percentage in the chat
- Copy Message - Copy agent responses with a single click using the new copy button
- Model Dropdown - Press Escape to dismiss the model selection dropdown
- Spec Rename - Rename specifications directly from the Kiro panel
Fixes (6)
- Markdown tables - Fixed rendering of tables in chat messages
- Chat fonts - Fixed inconsistent font styling in chat
- Context provider - Fixed context provider and right-aligned dropdown positioning
- Hook Cancellation - Fixed issue where hook commands couldn't be cancelled
- Powers - Fixed UI bugs for Kiro Powers panel
- Enterprise Profiles - Fixed profile switching for subscribed profiles
Patches (1)
- 0.8.86: Improved file write performance with batched streaming. Resolved file corruption caused by write race conditions, fixed supervised mode becoming unresponsive after accepting changes, and improved web tools reliability.

Includes 0.7.34 patch.

This release introduces Powers for dynamic MCP tool loading, conversation summarization to manage context windows, and slash commands for quick access to hooks and steering files.
Powers
Introducing Powers, a new way to give Kiro's agent instant expertise for any framework or tool. Powers package MCP servers, steering files, and hooks into reusable bundles that activate on-demand based on your conversation context. Instead of loading all MCP tools upfront and overwhelming your context window, powers load dynamically when you mention relevant keywords. Browse curated powers from launch partners including Datadog, Dynatrace, Figma, Neon, Netlify, Postman, Supabase, Stripe, and more—or create your own.
Summarization
Adds automatic conversation summarization to manage long conversations. When your conversation reaches 80% of the model's context window limit, Kiro automatically summarizes previous messages to bring context usage back below the limit. A new context usage meter in the chat panel shows what percentage of the model's context is being used.
Slash commands
Introducing slash commands for quick access to hooks and steering files directly from the chat input. Type / to see available commands and execute them instantly. Hooks with manual triggers and steering files configured with manual inclusion appear in the slash command menu, letting you run tests, sync documentation, or pull in specific guidance on demand.
Patches (3)
- 0.7.5: Fixed Powers installation failing when mcp.json contains comments
- 0.7.21: Added workspace trust check enforcement before loading context providers
- 0.7.34: Fixed authentication with socks proxies, chat session errors when opening folders, and MCP connectivity issues for IDC users during token refresh

Includes 0.7.21 patch.

This release introduces Powers for dynamic MCP tool loading, conversation summarization to manage context windows, and slash commands for quick access to hooks and steering files.
Powers
Introducing Powers, a new way to give Kiro's agent instant expertise for any framework or tool. Powers package MCP servers, steering files, and hooks into reusable bundles that activate on-demand based on your conversation context. Instead of loading all MCP tools upfront and overwhelming your context window, powers load dynamically when you mention relevant keywords. Browse curated powers from launch partners including Datadog, Dynatrace, Figma, Neon, Netlify, Postman, Supabase, Stripe, and more—or create your own.
Summarization
Adds automatic conversation summarization to manage long conversations. When your conversation reaches 80% of the model's context window limit, Kiro automatically summarizes previous messages to bring context usage back below the limit. A new context usage meter in the chat panel shows what percentage of the model's context is being used.
Slash commands
Introducing slash commands for quick access to hooks and steering files directly from the chat input. Type / to see available commands and execute them instantly. Hooks with manual triggers and steering files configured with manual inclusion appear in the slash command menu, letting you run tests, sync documentation, or pull in specific guidance on demand.
Patches (1)

This release adds support for enterprise billing where administrators can onboard large teams to Kiro, provides the capability to revert to the results of a previous conversation through checkpointing, adds support for multi-root workspaces, and introduces property-based testing with Kiro.
Spec correctness with property-based tests
Introduces property-based testing (PBT) to generate evidence for verification of spec requirements. Unlike unit tests, PBTs run hundreds of times with randomly generated inputs to detect edge cases.
Enterprise support
Launches support for enterprise users in Kiro IDE. Profile selection when multiple profiles are configured (auto-select default profile if only one profile exists), new dashboard for enterprise users, in-chat alerts, usage metering and summaries, enterprise governance of telemetry and MCP settings.
Kiro CLI
Introducing the Kiro CLI. Kiro CLI leverages the Auto agent to deliver results in your terminal, and takes you from natural language, to code, to deployment. Kiro CLI supports different agent modes, MCPs, steering files, and custom agents. Install on macOS or Linux:
curl -fsSL https://cli.kiro.dev/install | bash
Multi-root workspace support
With multi-root workspace support, a single Kiro workspace can have multiple roots, e.g., a single workspace that contains both /users/bob/my-project and /shared/utils/auth as top-level folders.
Checkpointing
Support for checkpointing which allows users to revert to the results of a previous conversation in Kiro. This feature enables developers to undo changes made by AI agents and return to a previous state of their workspace, while providing visibility into what changed and guidance on next steps.
Settings for context providers
Adds experimental settings to control the Codebase (#codebase) allowing users to opt-in to this CPU-intensive indexing feature.
Chat file context line ranges
Adds capabilities to the chat context provider for files to use line ranges in order to focus context to either a single line in a file or line range.
Kiro web dashboard
Access app.kiro.dev to manage your account, track usage statistics, and modify subscription settings through the web interface.
Improvements (5)
- Spec Workspace Folders - Fixes issue with spec context menu handling multi-root workspaces and align steering context menu descriptions
- Toolbar Button Contrast - Fixes issue with toolbar button contrast where inactive buttons had poor visibility against the toolbar background
- Modal Improvements - Fixed an issue where button styles were very inconsistent across the modal components and removal of excess border from header-only modals
- Deny list for Terminal Commands - Added check for denylist match at the beginning if a command can be auto-accepted
- Debugging - Include machine id in GitHub issues created through Kiro
- Steering Files - Improve steering file adherence to prevent guideline drift in long conversations by re-injecting always-included steering documents at regular intervals and refactor refine steering workflows
Fixes (7)
- Chat messages disappearing - Fixed issue where chat disappears and doesn't load anymore when the extension host reloads (which can happen through extension updates)
- MCP - Prevent URL double-encoding in MCP authorization redirect, update MCP features when Enterprise MCP disabled.
- Performance Improvements - Disable codebase indexing on startup that caused resources exhaustion, enhanced telemetry around agent event consumption, improved performance for file and folder context provider
- File-tree tool - Fixed issue where the file tree tool response was being removed when getting messages from previous execution
- Agent Workflow - Fixes an issue where messages are deleted if an exception is thrown while invoking agent, and fixed an issue where accept command failed didn’t work
- Windows - Prevent agent from writing into protected paths on Windows (example .vscode folder)
- Steering Files - Refactor refine steering work

This release introduces dev server support with background processes, spec context provider and MVP task workflows, enhanced MCP controls, and per prompt usage tracking with notifications.

Spec MVP Tasks UX
Choose your development pace during spec creation. When the agent generates tasks, select "Keep optional tasks (faster MVP)" to mark tests and documentation as optional (✱), or "Make all tasks required" for comprehensive coverage from the start. Optional tasks remain visible throughout the workflow, letting you focus on core features first
Spec Context in Chat
Video unavailable
Use #spec in chat to reference your spec files directly. The agent now understands your spec context, providing more accurate responses during development
Dev server support
Video unavailable
Long-running commands like npm run dev, build watchers, and test runners now start in the background automatically. The agent detects these processes, returns control to you immediately, and continues tracking them—no more blocked terminals
Per prompt credit consumption insights
Video unavailable
You can now see how many credits each prompt consumed, right in the chat panel.
Proactive Usage Notifications
Get intelligent alerts about your credit usage patterns to help you stay informed and avoid surprises

Agent Improvements
- Better Test Coverage: The agent now generates focused, meaningful tests instead of excessive test files, saving you time and credits
- More Concise Responses: Refined prompts make the agent more direct and to-the-point, reducing extensive summaries
- Repository Safety: In supervised mode, the agent automatically avoids writing to .git directories, protecting your repository integrity
User Experience Improvements
- Enhanced MCP Server Panel: Manage your MCP tools with new interactive controls—enable/disable individual tools, and see success indicators at a glance
- Cleaner Modal Interactions: Modals now block other keystrokes, allowing only Escape or click-to-close for a more predictable experience
- Billing Notifications: Access billing options directly from notification settings for easier account management
- Usage Meter: The status bar usage meter now updates correctly when you sign in or switch accounts
- Usage Summaries: Prefer minimal feedback? Disable execution usage summaries in settings
Bug Fixes
- MCP Server List: Fixed incorrect enabled/disabled status display when scrolling through long server lists
- Authentication: Improved error handling and reliability for authentication
- MCP Tool Call Persistence: Fixed issue where switching between sessions would cause MCP tool call approval prompts to disappear when returning to the original session
- Panel Layout: Removed chat panel from rearrangement destinations to prevent layout conflicts
- Status Bar Label: Simplified "Report a bug / Suggest an idea" to "Report issue"

This release improves agent reliability when creating and overwriting long files. We fixed a bug that prevented the agent from recovering from failures, improving overall stability.

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

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.

Hooks
Set up event-driven automation like updating documentation or generating tests on events such as file save.

Steering
Define steering files to guide agent behaviors.

Agentic chat
Build features from chat. Turn on Autopilot mode for hands-off execution or approve each change manually.

MCP
Integrate with your favorite tools and services.