> ## Documentation Index
> Fetch the complete documentation index at: https://kiro.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Quick start

> Get Crew running on your machine in five minutes — install, configure, and open the dashboard.

Crew is an open-source personal AI agent that runs locally or remotely on your hardware. It is persistent, self-learning, and self-evolving. You can work with it from the desktop app, web dashboard, and CLI, or additional channels such as Slack, Discord, Telegram, Teams, Webex, WeCom, and WeChat (Weixin). Multi-step tasks run unattended, recurring jobs run on your schedule, and heartbeats monitor systems until something needs attention.

## Install

### Desktop app

[Download Kiro Crew](https://kiro.dev/downloads) for macOS (signed `.dmg`), Windows (signed `.exe` installer), or Linux (`.deb`, `.rpm`, or `.AppImage`). The app starts a bundled Gateway when no local Gateway is already running. It can also connect to a remote Gateway over an SSH tunnel.

### One-line install

Install the prebuilt, SHA-256-verified wheel from the release CDN:

`curl -fsSL https://download.crew.kiro.dev/cli.sh | sh`

The installer installs through `pipx` when available or a managed venv at `~/.kiro/crew-venv`, and records the channel in `~/.kiro/crew/channel`.

After installing, configure and start the Gateway:

```bash
kirocrew setup        # interactive wizard: data dir, agent, credentials
kirocrew doctor       # verify everything is wired up
kirocrew gateway      # start the server → http://localhost:5476
```

Open `http://localhost:5476` in your browser. The first launch guides you through installing `kiro-cli` and completing sign-in. That's it — you're ready to chat.

**ℹ️ Info:** The desktop app handles gateway setup automatically — it starts a bundled Gateway on launch and guides sign-in from the app itself. These steps are only needed for the CLI-based install paths (one-line wheel, source build, Docker).

Semantic memory needs no setup. Embeddings run in-process and the Gateway downloads its model in the background on first start. Until it lands, memory search falls back to keyword matching and picks up embeddings automatically without a restart.

If you prefer to build from source, run in Docker, or set up Crew with the native Windows source install, see the full [Installation guide](https://kiro.dev/docs/crew/installation.md).

## Try it

Once the dashboard is open (either from the desktop app or at `http://localhost:5476`), here are a handful of workflows to explore.

### Chat

Type in the chat panel and press Enter. Each tab is an independent session with full tool access — read/write files, run commands, browse the web, or call any configured MCP tool. Sharpen a prompt with the prompt optimizer (Cmd/Ctrl+Shift+Enter).

### Run an autonomous task

Open the **Projects** panel, describe what you want, refine it into a spec, and hit **Run**. The [Task Runner](https://kiro.dev/docs/crew/features/task-runner.md) decomposes the spec into steps, executes them, runs tests, retries on failure, and checkpoints progress.

### Schedule a recurring job

Open the **Schedule** panel and add a job with natural language — or just ask in chat: "Every weekday at 9, summarize my open work." Jobs run in their own sessions. Results land in your dashboard notifications, Slack DM, or Telegram chat.

### Teach it preferences

Tell Crew something it should always remember in any chat session: "No, always run the frontend checks before calling a change done." It saves the correction as a lesson and applies it in future sessions.

### Delegate parallel work

Ask in chat: "Research these three options in parallel and recommend one." Crew spawns isolated subagents and synthesizes the results back into your conversation.

### Monitor something

Ask Crew to watch a system — in any chat session. Heartbeats check in on a schedule and alert when something needs attention. No manual polling loop required. Set one up from chat or via a cron job.

## Why Crew

**Persistent and always available.** Sessions, memory, schedules, and task checkpoints persist beyond one chat and across Gateway restarts. Scheduled, proactive, and reactive work continues without someone at the terminal.

**Self-learning.** Corrections and task failures become durable lessons that change later behavior. Preferences and project context carry across sessions.

**Self-evolving.** Repeated patterns can become reusable skills. Memory, lessons, and skills remain visible and editable, so your Crew becomes more tailored to you and your work over time.

**Runs where you choose.** Keep the runtime and its state on your own machine, in a local container, or on a remote machine you control.

**One Gateway, many ways to work.** The desktop app and web dashboard let you work directly. The Gateway connects that same runtime to Slack, Discord, Telegram, Teams, Webex, WeCom, WeChat (Weixin), and the CLI when you want to continue from another surface.

## What's next

 - [Chat](https://kiro.dev/docs/crew/chat.md) — Sessions, message controls, prompt optimizer, voice, and artifacts.
  - [Running 24/7](https://kiro.dev/docs/crew/running-24-7.md) — Run as a service, in Docker, on a remote host, or reach it from your phone.
 
  - [Features](https://kiro.dev/docs/crew/features.md) — Cron, subagents, task runner, snapshot, and artifact deploy.