Changelog

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.

This release introduces subagents for delegating complex tasks with live progress tracking, a built-in Plan agent for breaking down complex tasks into structured implementation plans, new grep and glob tools for fast file searching, multi-session support with an interactive session picker, and MCP registry support for governance.

Subagents

Delegate complex tasks to specialized agents with live progress tracking. Subagents run autonomously with their own context, enabling parallel task execution while keeping the main agent context focused. A default subagent is included for general-purpose tasks. You can also spawn subagents using your own agent configurations, allowing you to create specialized subagents tailored to specific workflows. Subagents have access to core tools including file read/write, shell commands, and MCP tools.

This feature introduces a new built-in tool: subagent. If you have an existing agent configuration that restricts available tools, add subagent to your allowed tools list.

Plan agent

The Plan agent is a specialized built-in agent that transforms ideas into structured implementation plans. Access it with Shift + Tab or the /plan command. Here's the workflow:

1. Requirements gathering - Structured questions with multiple choice options to refine your idea

2. Research & analysis - Explores your codebase using code intelligence, grep, and glob tools

3. Implementation plan - Creates detailed task breakdowns with clear objectives and demo descriptions

4. Handoff - Transfers the approved plan to the execution agent

The Planning agent operates in read-only mode—it can explore your codebase but cannot modify files, keeping focus on planning.

Grep and Glob Tools

Two new built-in tools for fast file searching:

• grep - Fast content search using regex. Respects `.gitignore`. Use instead of `grep`, `rg`, or `ag` commands in bash.

• glob - Fast file discovery using glob patterns. Respects `.gitignore`. Use instead of `find` command in bash.

Both tools are trusted by default in the current working directory and can be configured with allowedPaths and deniedPaths in your agent configuration.

Multi-Session Support

Work across multiple chat sessions with the new interactive session picker:

• kiro-cli chat --resume-picker - Open the session picker from command line

• kiro-cli chat --list-sessions - List all saved sessions

• /chat resume - Open session picker from within a chat

Sessions are automatically saved on every turn. The picker shows session name, last activity, and message preview.

MCP Registry Support

MCP registry support adds governance capabilities for MCP tools. Organizations can manage and control which MCP tools are available, ensuring consistency and security across teams.

We've added support for Claude Opus 4.5 to AWS IAM Identity Center users in both us-east-1 and eu-central-1 regions. Claude Opus 4.5 is available in both the Kiro IDE and Kiro CLI.

Loading image...

This release introduces code intelligence through LSP integration, knowledge index with agent schema configuration, enhanced auto-compaction, and improved guardrails for file reading.

Code Intelligence

Introducing Code Intelligence, bringing Language Server Protocol (LSP) integration to the Kiro CLI. The agent now has access to the same code understanding that powers Kiro IDE—go-to-definition, find references, hover information, and diagnostics. This enables more accurate code navigation, refactoring suggestions, and context-aware assistance across your entire codebase.

Knowledge Index

Adds Knowledge Index with agent schema configuration for Knowledge Bases and auto-indexing support. Define custom knowledge sources in your agent configuration to give it domain-specific context that automatically stays in sync with your codebase.

Includes 0.7.45 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

Loading image...

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.

We've added new web search and fetch capabilities to the Kiro CLI, enabling access to current information from the internet in real-time.

Loading image...

Added support for Claude Opus 4.5 - Anthropic's most intelligent model combining maximum capability with practical performance. Ideal for complex specialized tasks, professional software engineering, and advanced agents. Claude Opus 4.5 is available in both the Kiro IDE and Kiro CLI with experimental support.

Includes 0.6.32 patch.

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:

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

Loading image...

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

Loading image...

Access app.kiro.dev to manage your account, track usage statistics, and modify subscription settings through the web interface.