recall
Discuss a pilot

Quick Start

Build the Recall CLI from this workspace and run a local development instance.

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

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

Run the interactive setup wizard:

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

The wizard walks you through:

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

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

FilePurpose
recall.yamlDocker Compose configuration for all services
.envEnvironment variables, secrets, and API keys

Start Recall

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

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 in your browser.

System Architecture

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.
ServiceRole
WebDashboard UI and REST API
WorkerBackground scheduler that drives prompt runs
PostgresShared database and job queue
LLM APIsDirect API calls (OpenAI, Anthropic, OpenRouter)
LLM ScraperScrapers for ChatGPT, Claude, and Google AI Mode (BrightData, Oxylabs, Olostep)
Recall CLIGenerates recall.yaml + .env and runs docker compose

CLI Commands Reference

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

# 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

With Recall running, head to the User Guide to create your first brand, configure prompts, and start tracking AI visibility.

Was this page helpful?

View as Markdown