Persistent workspace memory
Kiro Crew keeps memory, lessons, and skills across sessions so the workspace can adapt to how you work. You can inspect, edit, scope, or delete what it carries forward.
Kiro Crew
Kiro Crew is an open source development workspace that remembers context, learns from corrections, and coordinates automated work across sessions. It supports local or remote use through a web dashboard, CLI, desktop app, and messaging integrations.
Overview
Kiro Crew is an open source development workspace that keeps working across sessions and restarts. It remembers project context, learns from corrections, and coordinates agents across scheduled jobs, webhooks, heartbeats, and other workflow triggers.
The product is designed for developers who want persistent context and unattended execution rather than a chat session that resets each time. It runs locally or remotely and is available through a web dashboard, CLI, desktop app, and messaging interfaces such as Slack, Telegram, and Discord.
Features
Editable lessons and skills
Corrections become durable lessons, and repeated workflows can be synthesized into named skills. Both are stored as Markdown files using the same steering file format as the IDE and CLI.
Searchable project knowledge
A knowledge graph backed by vector embeddings and full-text search stores architectural decisions, coding preferences, and project context. The agent can retrieve relevant context instead of re-reading everything.
Autonomous task execution
Cron schedules, webhooks, and heartbeat monitors let Kiro Crew continue work while you are away. Long-running tasks move through checkpoints, validation, and retries automatically.
Layered security controls
The page describes built-in defenses including OS sandboxing, denied command patterns, bash blocking, input/output validation, sensitive path protection, credential redaction, and signed audit logs.
Apps and SDK extensibility
Kiro Crew can be extended with custom apps built in TypeScript or Python through the SDK. Apps can register MCP tools, subscribe to agent events, and persist state between sessions.
Use Cases
Persistent development across sessions
Use Crew when you want a workspace that carries project context forward instead of starting from scratch after every session. It is suited to ongoing development work where decisions, preferences, and corrections should stay available.
Unattended operational workflows
Use scheduled jobs, webhooks, and heartbeat monitors to let agents handle recurring or event-driven work without constant supervision. The page points to maintenance tasks, pipeline reactions, and long-running work with checkpoints and retries.
Context-aware code and project decisions
Use the knowledge graph and searchable memory to pull up architectural decisions, coding conventions, and project-specific notes during active development. This helps the agent retrieve relevant context instead of re-reading the entire workspace.
Custom internal tools and automations
Use the SDK when you need project-specific automation that does not fit a plain chat interface. Apps can add custom UIs, event subscriptions, state persistence, and MCP tools for specialized workflows.
Team collaboration in chat channels
Use messaging surfaces such as Slack, Telegram, or Discord when your team wants to interact with the same agent crews from existing channels. The source says each Slack thread can become an isolated AI session with full tool access.
Pros and Cons
Pros
- Keeps memory, lessons, and skills across sessions so users do not have to re-establish context repeatedly.
- Supports unattended work through schedules, webhooks, heartbeats, checkpoints, validation, and retries.
- Offers multiple access surfaces, including web dashboard, CLI, desktop app, and messaging integrations.
- Provides built-in security controls and open-source transparency so the workspace can be inspected and adapted.
- Can be extended with custom apps and SDK-based automation for project-specific workflows.
Cons
- The source does not provide a full technical spec for every integration, so some workflow details are still partial on the page.
- Pricing and plan details are split across product, pricing, and billing pages, so readers may need to check multiple pages for the full subscription picture.
FAQ
What is Kiro Crew?
Kiro Crew is an open source development workspace that runs on your own machine and keeps working across sessions. It remembers project context, turns corrections into lasting lessons, and can run scheduled or long-running tasks unattended.
Where can I use Kiro Crew?
The page describes Crew as working across Mac, Linux, and Windows. It can run locally or be deployed remotely, and it is also available through a web dashboard, CLI, desktop app, and messaging surfaces such as Slack, Telegram, and Discord.
Can Kiro Crew run tasks unattended?
Kiro Crew supports scheduled jobs, webhook triggers, and heartbeat monitors so agents can continue working while you are away. The page says long-running tasks move through checkpoints, validation, and retries automatically.
How does Kiro Crew keep context across sessions?
The source shows that Kiro Crew uses markdown-based lessons and skills, a knowledge graph with vector embeddings and full-text search, and apps built with the SDK. It also says it is built on the Kiro CLI and shares the same agent protocol, model support, and .kiro configuration.
Is Kiro Crew open source and secure?
The page says Kiro Crew is fully open source and built with layered security controls, including sandboxing, denied command patterns, bash blocking, input/output validation, sensitive path protection, credential redaction, signed audit logs, and dashboard token auth. The source does not provide a single consolidated enterprise security specification beyond those controls.
Quick Facts
- Category
- Developer Tool
- Product type
- Open source development workspace
- Platform
- Mac, Linux, Windows
- Access methods
- Web dashboard, CLI, desktop app, Slack, Telegram, Discord
- Core workflow
- Persistent memory, autonomous agents, schedules, webhooks, and checkpoints
- Source domain
- kiro.dev
Kiro Crew 대안
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
hob
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
Biji
Biji는 혁신적인 도구와 기능을 통해 생산성을 향상시키기 위해 설계된 다목적 플랫폼입니다.
Manta AI
Manta AI is an autonomous web app testing tool for teams that want to map application behavior, catch regressions, and generate tests without writing scripts or maintaining selectors. It works from a URL and supports plain-English test flows, run results with screenshots, and scheduled or deployment-triggered checks.
Redline
Redline is a budgeting tool for Claude Code that paces sessions to stay within time, token, cost, or plan-percentage limits. It uses Claude Code’s native hooks and statusline to help sessions finish with a usable result instead of stopping abruptly.