Added: Kiro CLI leverages the Kiro Auto agent to deliver the best results at the best price, in your terminal, and takes you from natural language, to code, to deployment. Kiro CLI supports different agent modes, MCPs, Kiro steering files, and custom agents, allowing you to mold the CLI to meet your needs.
Added: Kiro CLI announcement. Learn more at kiro.dev/cli-upgrade
This release expands MCP capabilities with remote server support and one-click installation, introduces global steering rules and project-specific agent configuration, and refines agent workflows with improved hook execution, command trust, and targeted file context.
Connect to MCP servers hosted anywhere on the internet via Streamable HTTP, accessing cloud services and APIs without local installation.
Define global steering rules that apply across all your workspaces.
Support for the AGENTS.md standard to define guidelines, coding standards and architectural patterns. Add an AGENTS.md file to the global steering file location (~/.kiro/steering/), or to the root folder of your workspace, and they will get picked up by Kiro automatically.
Simplified MCP server setup with automatic installation—get started with MCP tools faster than ever. View servers →
Use environment variables in your MCP server configurations for flexible, environment-specific setups.
![## Use Case 3: Extending User Preferences
**Scenario**: Add a "preferredPaymentMethod" field to UserPreferences
**Targeted Context Needed**:
#IIfile:src/types/app.ts:127-143]]
This shows just the UserPreferences interface, which is what needs modification. The agent doesn't need to see:
- The full User interface (lines 115-126)
- Payment method enums (lines 105-112)
- Subscription types (lines 158-180)
**Result**: Faster, more accurate implementation with less context pollution.](/images/changelogs/v0.5.0/targeted-context.png?h=e6ee3581)
Reference specific line ranges when adding files to context (e.g., #[[file:src/utils/helper.ts:10-25]]), giving you precise control over what the agent sees and enabling more focused implementations.
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.
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
Use #spec in chat to reference your spec files directly. The agent now understands your spec context, providing more accurate responses during development
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
You can now see how many credits each prompt consumed, right in the chat panel.
Get intelligent alerts about your credit usage patterns to help you stay informed and avoid surprises
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
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
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 brings spec task management, intelligent code diagnostics, AI-powered commit messages, and refined agent interactions to streamline your development process.
Support for Sonnet 4.5 (experimental): You can now send your prompts to Sonnet 4.5 via the chat box. Sonnet 4.5 is also available in Auto, our agent which uses a variety of task-specific foundation models under the hood
Spec MVP tasks: During spec creation, you can now mark tasks (including unit tests) as optional to prioritize core features while keeping comprehensive task lists
Diagnostics Tool: Added diagnostics tool to provide agent with syntax, type, and semantic errors, improving agent accuracy and reducing lint errors
Git Commit Message Generation: Draft commit messages using the agent directly from the source control pane with a single click. Learn more →
Repetitive Tool Use Detection: Agent now detects repetitive tool usage patterns and prompts users to continue or stop, optimizing credit consumption
Unified Credits System improvements: Unified credits system with Auto agent capabilities enhancements and bug fixes. This feature provides users a single credit pool and streamlined usage tracking. Learn more →
Long Running Commands: Enhanced executeBash tool to detect and avoid commands like dev servers, test runners, interactive commands etc.
Usage Meter: Usage meter now properly refreshes when switching between accounts within the same session
Credit Usage Persistence: Improved credit usage tracking across account switches and session management
Context Popup Positioning: Improved positioning of the context popup triggered by # in chat - now consistently appears at the top-left of the input container
Theme Compatibility: Enhanced visibility of the overage toggle and improved account dashboard access in Light High Contrast, Kiro Light, Light+, and Quiet Light themes
Remote Workspace Reliability: Fixed issues with extension loading in untrusted workspaces when connecting to remote hosts
Updated Model Selection Setting: Introduced new kiroAgent.modelSelection setting, replacing the deprecated kiroAgent.agentModelSelection for model management
This release addresses critical security vulnerabilities and bug fixes.
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
License Access: Fixed render issue in License page
This release brings Auto, our new agent, enhanced usage tracking, and editor improvements to elevate your development experience.
Note: These features are rolling out gradually between now and October 1st, and users will be migrated to a single pool of credits and new limits. Your limits will reset to the new monthly plan limits once migrated.
Auto: Added Auto to the model options. Auto is an agent that uses a mix of different frontier models such as Sonnet 4 combined with specialized models, and optimization techniques such as intent detection, caching, and more
Unified Limits: Support for new paid plans with unified limits and fractional credit consumption
Usage Dashboard: Support to view usage based on single Kiro credit pool
Usage Meter: Add credit consumption status bar item to allow easier usage tracking
Editor Upgrade: Upgraded editor to CodeOSS 1.103.2
Account Management: Enable Kiro account deletion for BuilderID
Authentication: Improvements to login reliability and logout flow for better signing experience
UI Improvements: Hide trust command UI on command cancellation
This release includes editor performance improvements, enhanced reliability, and bug fixes to enhance your development experience.
Code OSS v1.100.3 Upgrade: Updated to Code OSS v1.100.3 that adds improved stability and performance improvements
Faster Response Times: Optimized request handling makes interactions more efficient and improves performance
Improved Session Management: Enhanced backend processing reduces interruptions and allows for longer continuous work sessions
Enhanced Tool Call Recovery: When tool invocations result in repeated failures, Kiro now prompts for your intervention instead of continuing indefinitely, protecting your usage limits and preventing loops
Enhanced Security Patterns: Expanded detection of dangerous shell commands with improved pattern recognition. Risky commands require manual review unless you explicitly trust them. Learn more about security patterns →
Model Update: Removed Claude Sonnet 3.7 from the model selector and set Claude Sonnet 4 as the default for all users. Sonnet 4 delivers improved performance and capabilities across all interactions.
Git Repository Initialization: Fixed issue that prevented Git setup for new projects without existing repositories
Model Selection Persistence: Fixed chat model selection not being saved when restarting Kiro IDE
This release brings key improvements to accessibility, account management, and overall platform reliability.
Kiro is now accessible to more developers through waitlist codes. If you have an waitlist code, you can register and start building with AI-powered development workflows alongside our growing community.
Paid plans are now live, giving you access to higher usage limits. Choose the plan that fits your development needs and scale your AI-powered workflows.
Introducing comprehensive usage tracking to help you monitor your Kiro consumption. The new billing dashboard displays real-time spec and vibe request usage, plan management options, and overage controls for paid plans.
Enhanced Command Trust: Improved handling of piped commands (ls -la | grep ".js") with clearer trust requirements for command chains.
Workspace Protection: Improved file system tool restrictions to better prevent accidental external modifications
Command Boundary: Commands with potentially dangerous patterns now require manual approval unless explicitly trusted.
Automatic Retries: Failed backend requests are automatically retried for improved reliability
Optimized Model Efficiency: Improvements to optimize frontier model usage with Sonnet
Light Mode Improvements: Resolved theming issues for better visual consistency
Clearer Login Errors: More helpful error messages when authentication fails