# Quick Start (/docs/getting-started)



## Prerequisites [#prerequisites]

* **Docker** — Docker Engine 24+ with Docker Compose v2
* **Node.js** — 24.x (for the CLI)
* **pnpm** — 11.x
* At least one AI provider API key (OpenAI or Anthropic)

## Build the CLI [#build-the-cli]

```bash
pnpm install
pnpm --filter @dorecall/cli build
pnpm --filter @dorecall/cli exec recall --help
```

The branded CLI and container images are not yet published to public
registries. For a production pilot, use the deployment runbook included in the
workspace; use the CLI's `--dev` mode for a local source build.

## Initialize Your Instance [#initialize-your-instance]

Run the interactive setup wizard:

```bash
pnpm --filter @dorecall/cli exec recall init --dev
```

The wizard walks you through:

. **Config directory** — Where to store your `recall.yaml` and `.env` files (default: `./recall`)
. **PostgreSQL** — Run Postgres in Docker (recommended) or provide an existing `DATABASE_URL`
. **AI Providers** — Configure scrapers (BrightData, Oxylabs, Olostep, DataForSEO) and/or direct model APIs (OpenAI, Anthropic, Mistral, OpenRouter); see [Providers](/docs/user-guide/providers) for details
. **Start** — Optionally start the stack immediately

Once complete, Recall generates two files in your config directory:

| File          | Purpose                                       |
| ------------- | --------------------------------------------- |
| `recall.yaml` | Docker Compose configuration for all services |
| `.env`        | Environment variables, secrets, and API keys  |

## Start Recall [#start-recall]

If you didn't start during init, bring everything up with:

```bash
pnpm --filter @dorecall/cli exec recall compose up -d
```

This builds the local images and starts all services. Once they report healthy, open **[http://localhost:1515](http://localhost:1515)** in your browser.

## System Architecture [#system-architecture]

<img src="/brand/architecture.svg" alt="Recall system architecture: User connects to Web; Web and Worker share a Postgres database; Web calls LLM APIs; Worker calls both LLM APIs and an LLM Scraper." className="my-6 w-full" />

| Service         | Role                                                                            |
| --------------- | ------------------------------------------------------------------------------- |
| **Web**         | Dashboard UI and REST API                                                       |
| **Worker**      | Background scheduler that drives prompt runs                                    |
| **Postgres**    | Shared database and job queue                                                   |
| **LLM APIs**    | Direct API calls (OpenAI, Anthropic, OpenRouter)                                |
| **LLM Scraper** | Scrapers for ChatGPT, Claude, and Google AI Mode (BrightData, Oxylabs, Olostep) |
| **Recall CLI**  | Generates `recall.yaml` + `.env` and runs `docker compose`                      |

## CLI Commands Reference [#cli-commands-reference]

Once Recall is running, these commands help you manage it:

```bash
# View live logs
recall compose logs -f

# View logs for a specific service
recall compose logs -f web

# Check service status
recall compose ps

# Stop all services
recall compose down
```

## What's Next [#whats-next]

With Recall running, head to the [User Guide](/docs/user-guide) to create your first brand, configure prompts, and start tracking AI visibility.