Crew - Kiro
Loading image...
svg]:h-6 [&>svg]:w-6 text-purple-300">
Persistent and self-improving<br>p>a:hover]:text-prey-200 [&>p>a]:underline">Memory, lessons, and skills carry across sessions, so your crew evolves to fit your work. Inspect, edit, or remove what your crew carries forward.
svg]:h-6 [&>svg]:w-6 text-purple-300">
Works while you’re away<br>p>a:hover]:text-prey-200 [&>p>a]:underline">Cron schedules, webhook triggers, and heartbeat monitors keep your agent crews productive online or off. Long-running tasks move through checkpoints, validation, and retries automatically. Fold in your unique workflows and tools with Apps.
svg]:h-6 [&>svg]:w-6 text-purple-300">
7 layers of defense<br>p>a:hover]:text-prey-200 [&>p>a]:underline">OS sandboxing, denied command patterns, bash blocking, input/output validation, sensitive path protection, credential redaction, and signed audit logs. Verify every layer: it’s open source.
Learns how you work<br>Kiro Crew remembers context across sessions, turns corrections into lasting lessons, and evolves from your work patterns so it just keeps getting better.
Loading image...
Loading image...
Control what your crew learns<br>p>a:hover]:text-prey-200 [&>p>a]:underline">Corrections become durable lessons, and repeated workflows get synthesized into named skills. Lessons and skills are Markdown files you can inspect, edit, scope to a workspace, or delete — and they use the same steering file format as the IDE and CLI.
Loading image...
Knowledge graph with search<br>p>a:hover]:text-prey-200 [&>p>a]:underline">Architectural decisions, coding preferences, and project context land in a knowledge graph backed by vector embeddings and full-text search, so the agent retrieves what's relevant instead of re-reading everything.
Loading image...
Memory that survives restarts<br>p>a:hover]:text-prey-200 [&>p>a]:underline">Active projects and working context persist across sessions and restarts. Long-running work checkpoints and resumes, so you're not re-prompting your way back to where you left off.
Keeps working while you’re away<br>Agents work in parallel with scheduled jobs, webhooks, and heartbeats, so your crew runs tasks end to end and discovers work worth doing even when you step away.
Loading image...
svg]:h-6 [&>svg]:w-6 text-purple-300">
Issues<br>p>a:hover]:text-prey-200 [&>p>a]:underline">Scans your backlog for work that's actionable now (reproducible bugs, stale issues, missing tests) and picks up what it can finish without waiting to be asked.
svg]:h-6 [&>svg]:w-6 text-purple-300">
Codebase<br>p>a:hover]:text-prey-200 [&>p>a]:underline">Watches for drift: dependencies falling behind, dead branches, failing test suites, docs that no longer match the code.
svg]:h-6 [&>svg]:w-6 text-purple-300">
CI/CD<br>p>a:hover]:text-prey-200 [&>p>a]:underline">Reacts to pipeline and deployment events. A failed build or a broken deploy becomes a session with the logs already in context.
svg]:h-6 [&>svg]:w-6 text-purple-300">
Schedules<br>p>a:hover]:text-prey-200 [&>p>a]:underline">Timezone-aware cron jobs for recurring work. Per-job timeouts, jitter to avoid thundering herds, and skip dates for maintenance windows. Every run is logged and checkpointed.
svg]:h-6 [&>svg]:w-6 text-purple-300">
Webhooks<br>p>a:hover]:text-prey-200 [&>p>a]:underline">Point external events at your agent over authenticated endpoints and it starts working on arrival.
svg]:h-6 [&>svg]:w-6 text-purple-300">
Heartbeat<br>p>a:hover]:text-prey-200 [&>p>a]:underline">Watches state changes in your PRs, deployments, and pipelines, triggering work when conditions are met, so the agent stays in the loop without polling.
Apps and extensibility<br>Purpose-built interfaces for work that doesn't belong in chat. Wrap agents, skills, schedules, and integrations in a custom UI to automate your day without chatting every instruction.
Loading image...
Loading image...
Agent Worlds<br>Your running agents viewable as characters in various themed worlds, so a glance tells you how busy your crew is. Pop it out to a second screen.
Loading image...
Research Lab<br>Give it a question and it fans out into narrower sub-questions, sends agents after each one, and streams findings in as they land.
Loading image...
Code Review Sage<br>Reviews each changed file in its own agent session, weights them by blast radius, and stages a draft GitHub review that stays unpublished until you submit.
typescriptdeploy-monitor/index.tsx<br>import { defineApp, useAgent } from '@kirocrew/app-sdk'
export default defineApp({<br>name: 'deploy-monitor',<br>skills: ['./skills/deployment-check.md'],<br>schedule: '*/15 * * * *',<br>ui: () => DeploymentDashboard />,<br>})
Build Apps in TypeScript or Python with the SDK<br>The App SDK gives you typed bindings for the agent runtime, skill system, and event bus. Define your App’s UI in React (rendered in the dashboard) or expose it headlessly via the CLI. Apps can register their own MCP tools, subscribe to agent events, and persist state between...