> ## Documentation Index
> Fetch the complete documentation index at: https://nextmind-85153aa2-dev.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Get a working Mycel agent in 5 minutes

## Prerequisites

* Python 3.11+
* Node.js 18+
* An OpenAI-compatible API key (Anthropic, OpenAI, OpenRouter, etc.)

## Install and run

<Steps>
  <Step title="Clone the repository">
    ```bash theme={null}
    git clone https://github.com/OpenDCAI/Mycel.git
    cd Mycel
    ```
  </Step>

  <Step title="Install dependencies">
    ```bash theme={null}
    # Backend
    uv sync

    # Frontend
    cd frontend/app && npm install && cd ../..
    ```
  </Step>

  <Step title="Start services">
    Open two terminals:

    ```bash theme={null}
    # Terminal 1 — backend
    uv run python -m backend.web.main
    # Listening at http://localhost:8001
    ```

    ```bash theme={null}
    # Terminal 2 — frontend
    cd frontend/app && npm run dev
    # Listening at http://localhost:5173
    ```
  </Step>

  <Step title="Configure your LLM provider">
    1. Open **[http://localhost:5173](http://localhost:5173)** and register an account
    2. Go to **Settings → Models**
    3. Enter your API key and choose a model

    <Tip>
      Mycel supports any OpenAI-compatible endpoint. If you use Anthropic directly, set your `ANTHROPIC_API_KEY`. For OpenRouter, set `OPENAI_API_KEY` with your OpenRouter key and `https://openrouter.ai/api/v1` as the base URL.
    </Tip>
  </Step>

  <Step title="Chat with your first agent">
    Navigate to the chat view and start a new conversation. The built-in **Mycel** agent is ready to use immediately.

    Try asking it to:

    * Read a file from your workspace
    * Search the codebase
    * Run a shell command
  </Step>
</Steps>

## Add a sandbox (optional)

By default, agents run on your local machine. To isolate execution in a container:

<Steps>
  <Step title="Install Docker">
    Make sure Docker is running on your machine.
  </Step>

  <Step title="Enable Docker in settings">
    Go to **Settings → Sandbox**. Expand the Docker card, set the image (default: `python:3.12-slim`), and click Save.
  </Step>

  <Step title="Start a sandboxed thread">
    In the new conversation view, select **docker** from the sandbox dropdown before sending your first message. All subsequent agent runs in this thread use the same isolated container.
  </Step>
</Steps>

## Try multi-agent chat

Mycel's social layer lets agents message each other — and you — like a group chat.

<Steps>
  <Step title="Create a second agent">
    Go to the Agent list and create a new Agent. Give it a name and a system prompt (e.g., "You are a code reviewer").
  </Step>

  <Step title="Open a chat with it">
    Go to the **Chat** view, find your new agent in the directory, and start a conversation.
  </Step>

  <Step title="Let agents talk to each other">
    In the first agent's thread, tell it to message your code reviewer: "Ask the code reviewer to look at this function." The agent will call `send_message` and the reviewer will respond autonomously.
  </Step>
</Steps>

## Next steps

<CardGroup cols={2}>
  <Card title="Core concepts" icon="book" href="/en/concepts">
    Understand Agent Configs, Agent Users, Threads, Skills, Tasks, and Resources
  </Card>

  <Card title="Sandbox providers" icon="box" href="/en/sandbox">
    Docker, E2B, Daytona, AgentBay — isolated execution environments
  </Card>

  <Card title="Configuration" icon="gear" href="/en/configuration">
    Models, tools, skills, memory tuning
  </Card>

  <Card title="Deployment" icon="cloud" href="/en/deployment">
    Run Mycel in production
  </Card>
</CardGroup>