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

# Quick Start

> Install MIRA, connect a provider, and get your first answer in under 5 minutes.

This guide gets MIRA running as fast as possible. If you want platform-specific detail, see the [Installation](/get-started/installation/macos) pages.

## Step 1 — Download

Go to [GitHub Releases](https://github.com/satyendra2013/mira-app/releases/latest) and download the installer for your platform:

| Platform                  | File                                                                          |
| ------------------------- | ----------------------------------------------------------------------------- |
| **macOS** (Apple Silicon) | `MIRA-x.x.x-arm64.dmg`                                                        |
| **Windows**               | `MIRA-Setup-x.x.x-x64.exe`                                                    |
| **Linux**                 | `MIRA-x.x.x-x64.AppImage`, `mira_x.x.x_amd64.deb`, or `mira-x.x.x-x86_64.rpm` |

## Step 2 — Install and launch

<Tabs>
  <Tab title="macOS">
    1. Open the downloaded `.dmg`
    2. Drag **MIRA** to your **Applications** folder
    3. Launch MIRA from Applications or Spotlight
    4. If macOS shows *"cannot be opened"*, go to **System Settings → Privacy & Security → Open Anyway**
  </Tab>

  <Tab title="Windows">
    1. Run `MIRA-Setup-x.x.x-x64.exe` — no administrator rights required
    2. Launch from the Start Menu or Desktop shortcut
  </Tab>

  <Tab title="Linux">
    ```bash theme={null}
    # AppImage — no install required
    chmod +x MIRA-x.x.x-x64.AppImage
    ./MIRA-x.x.x-x64.AppImage

    # Debian/Ubuntu
    sudo dpkg -i mira_x.x.x_amd64.deb
    ```
  </Tab>
</Tabs>

## Step 3 — First launch setup

On first launch, MIRA automatically:

1. Sets up a bundled Python 3.11 virtual environment
2. Installs all required Python dependencies

A splash screen is shown during this one-time setup. Watch the status bar — when it shows **NAE ready**, setup is complete. This takes approximately **60 seconds** and runs once only.

<Info>
  **Python is bundled.** MIRA ships a self-contained Python 3.11 runtime. You do not need Python on
  your `PATH` and never need to run `pip install` manually.
</Info>

## Step 4 — Connect your LLM provider

Open **Settings** (⌘,) and configure one provider:

<Tabs>
  <Tab title="AWS Bedrock">
    Go to **Settings → Bedrock / AWS** and enter:

    * AWS Access Key ID
    * AWS Secret Access Key
    * AWS Region (e.g. `eu-west-1`)

    Click **Test Connection** — MIRA calls `sts:GetCallerIdentity` and displays your Account ID on success.

    Minimum IAM policy required:

    ```json theme={null}
    {
      "Effect": "Allow",
      "Action": ["bedrock:InvokeModel", "bedrock:InvokeModelWithResponseStream"],
      "Resource": "arn:aws:bedrock:*::foundation-model/anthropic.claude-*"
    }
    ```
  </Tab>

  <Tab title="Anthropic">
    Go to **Settings → API Tokens**, add a token with label `ANTHROPIC_API_KEY`, and paste your key from [console.anthropic.com](https://console.anthropic.com).
  </Tab>

  <Tab title="OpenAI">
    Go to **Settings → API Tokens**, add a token with label `OPENAI_API_KEY`, and paste your key from [platform.openai.com](https://platform.openai.com).
  </Tab>

  <Tab title="Ollama (no key needed)">
    1. Install [Ollama](https://ollama.com) and start it
    2. Pull a model: `ollama pull llama3`
    3. In **Settings → Engine**, set the Ollama base URL to `http://localhost:11434`

    No API key, no account, no network calls for queries.
  </Tab>
</Tabs>

## Step 5 — Send your first query

1. Click **New Chat** (or ⌘N)
2. Type a question — something specific to your work
3. Press **Enter**

Watch MIRA reason through the answer in real time. Streaming output appears token by token.

<Tip>
  Try a question that requires multiple steps — MIRA's strengths are multi-hop reasoning and
  verified answers. A simple factual question works too, but won't show the full capability.
</Tip>

## What's next?

<CardGroup cols={2}>
  <Card title="Understand the two engines" icon="cpu" href="/core-concepts/reasoning-engines">
    NAE vs RLM — when to use each
  </Card>

  <Card title="Upload a document" icon="file-text" href="/features/document-context/uploading-documents">
    Add PDFs, CSVs, and code files to your session
  </Card>

  <Card title="Apply a Skill" icon="wand" href="/features/skills/built-in-skills">
    Give MIRA a specialised reasoning persona
  </Card>

  <Card title="Run a Workflow" icon="git-branch" href="/features/workflows/built-in-workflows">
    Chain reasoning into a repeatable pipeline
  </Card>
</CardGroup>