Configuration

Environment variables, deployment modes, and advanced configuration options.

Deployment Modes

Recall supports several deployment modes, controlled by the DEPLOYMENT_MODE environment variable:

ModeDescription
localSingle-org, email/password auth. Best for individual use. (default)
demoRead-only mode for showcasing Recall without allowing changes.
cloudManaged hosting (coming soon).

Environment Variables

When you run recall init, the CLI generates a .env file in your config directory. You can edit this file directly to change settings.

Core Settings

VariableDescriptionDefault
DEPLOYMENT_MODEDeployment modelocal
DATABASE_URLPostgreSQL connection stringGenerated by CLI
BETTER_AUTH_SECRETSecret key for session encryptionAuto-generated
DISABLE_TELEMETRYSet to 1 to disable all telemetry. See Telemetry.—
DEFAULT_DELAY_HOURSHow often each enabled prompt is re-run against the AI models, in hours.24

DEFAULT_DELAY_HOURS only takes effect for prompts scheduled after you change it. Prompts that are already scheduled keep the cadence they were created with, even after a restart. To apply a new cadence to an existing prompt, disable it and then re-enable it under Settings → Prompts — re-enabling reschedules it at the current DEFAULT_DELAY_HOURS.

AI Provider Keys

At least one provider is required for Recall to track visibility. See Providers for a full cost/capability breakdown and recommended setups.

VariableDescription
BRIGHTDATA_API_TOKENBrightData token — recommended scraper for ChatGPT + Google AI Mode. Sign up
OXYLABS_USERNAMEOxylabs Web Scraper API username — alternative scraper for ChatGPT, Perplexity, Google AI Mode. Sign up
OXYLABS_PASSWORDOxylabs Web Scraper API password
OLOSTEP_API_KEYOlostep key — recommended scraper, powers most large-scale trackers. Sign up
OPENAI_API_KEYOpenAI API key — enables ChatGPT (via API, not the consumer UI)
ANTHROPIC_API_KEYAnthropic API key — enables Claude tracking
OPENROUTER_API_KEYOpenRouter key — one key for Claude + other hosted models
DATAFORSEO_LOGINDataForSEO login — optional, enables DataForSEO targets such as google-ai-mode:dataforseo:online, chatgpt:dataforseo:online, perplexity:dataforseo:online, and gemini:dataforseo:online
DATAFORSEO_PASSWORDDataForSEO password
SCRAPE_TARGETSComma-separated model:provider[:version][:online] entries. See Providers.

Updating Configuration

To change environment variables after initial setup:

# Edit the .env file
nano ~/.recall/.env

# Restart services to pick up changes
recall compose down
recall compose up -d

Using an External Database

By default, recall init provisions a PostgreSQL container. To use an existing database instead, choose "Use existing Postgres" during recall init and provide your connection string when prompted.

Your database must be PostgreSQL 15 or later.

Was this page helpful?