Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.bumbleagi.com/llms.txt

Use this file to discover all available pages before exploring further.

Set variables in .env at the repo root (gitignored, loaded automatically) or as system/Railway env vars.

Platform tokens

VariablePurpose
TELEGRAM_TOKENTelegram bot token (must match token_env in entity YAML)
DISCORD_TOKENDiscord bot token
BUMBLEBEE_TELEGRAM_OPERATOR_IDSComma-separated Telegram user IDs for /privacy operators. Merged with YAML operator_user_ids.

Deployment

VariableDefaultPurpose
BUMBLEBEE_DEPLOYMENT_MODElocallocal or hybrid_railway
BUMBLEBEE_INFERENCE_PROVIDERderivedlocal, remote_gateway (home tunnel gateway), openrouter, or venice (hosted OpenAI-compatible APIs for optional harness testing). See Hosted inference (testing).
BUMBLEBEE_INFERENCE_BASE_URLGateway: tunnel root URL (no path). Hosted presets: optional override; otherwise defaults are baked in per provider. Must always be the root before /v1.
BUMBLEBEE_INFERENCE_TIMEOUT120Inference request timeout (seconds)
BUMBLEBEE_INFERENCE_GATEWAY_TOKENBearer token for remote_gateway (home inference gateway)
BUMBLEBEE_INFERENCE_API_KEY_ENVEnv var name for the Bearer token (gateway or hosted, depending on provider)
BUMBLEBEE_INFERENCE_PASS_NUM_CTXtrue / false: send Ollama-style options.num_ctx on chat. Use false for strict OpenAI-compatible hosts (OpenRouter, Venice, etc.).
OPENROUTER_API_KEYBearer key when BUMBLEBEE_INFERENCE_PROVIDER=openrouter (unless overridden via BUMBLEBEE_INFERENCE_API_KEY_ENV / YAML).
VENICE_API_KEYBearer key when BUMBLEBEE_INFERENCE_PROVIDER=venice (unless overridden).
BUMBLEBEE_TIMEZONEIANA timezone (e.g. America/New_York)

Ollama

VariableDefaultPurpose
OLLAMA_HOSThttp://127.0.0.1:11434Override Ollama URL

Database

VariablePurpose
DATABASE_URLPostgres connection string. When set, all structured memory uses Postgres instead of SQLite.

Execution

VariableDefaultPurpose
BUMBLEBEE_EXECUTION_RPC_URLRemote execution host URL
BUMBLEBEE_EXECUTION_RPC_TOKENBearer token for execution RPC
BUMBLEBEE_EXECUTION_WORKSPACE_DIRPin workspace root (e.g. /app/data on Railway). Also anchors the persistent venv ($WORKSPACE/.venv) and HOME for Railway entrypoint.
BUMBLEBEE_SKIP_VOLUME_VENV0Set to 1 to use the image Python instead of $WORKSPACE/.venv (debug only).
BUMBLEBEE_VOLUME_HOME$WORKSPACE/.homeOverride HOME on the volume (pip / Playwright caches).
BUMBLEBEE_EXECUTION_REQUIRE_RAILWAYfalseBlock all local execution when not on Railway

Home gateway

VariableDefaultPurpose
BUMBLEBEE_PYTHONOptional full path to python3 for scripts/gateway.sh when the interpreter on PATH is not the one with Bumblebee installed (common on macOS with multiple Pythons).
INFERENCE_GATEWAY_TOKENBearer token (must match worker’s BUMBLEBEE_INFERENCE_GATEWAY_TOKEN)
OLLAMA_BASE_URLhttp://127.0.0.1:11434Upstream Ollama URL
INFERENCE_GATEWAY_HOST127.0.0.1Gateway listen address
INFERENCE_GATEWAY_PORT8010Gateway listen port
INFERENCE_GATEWAY_BACKEND_TIMEOUT120Timeout for Ollama requests
INFERENCE_GATEWAY_MAX_BODY_BYTES8000000Max request body size

Object storage

VariablePurpose
BUMBLEBEE_ATTACHMENTS_BACKENDlocal_disk or object_s3_compat
BUMBLEBEE_S3_ENDPOINT_URLS3-compatible endpoint
BUMBLEBEE_S3_BUCKETBucket name
BUMBLEBEE_S3_ACCESS_KEYAccess key
BUMBLEBEE_S3_SECRET_KEYSecret key

Optional tools

VariablePurpose
FIRECRAWL_API_KEYFirecrawl key for enhanced web search/scrape
FAL_API_KEYFal key for image generation
HOME_ASSISTANT_URLHome Assistant API URL for IoT tools
HOME_ASSISTANT_TOKENHome Assistant Long-Lived Access Token
MASTODON_URLMastodon instance URL for social broadcast tools
MASTODON_ACCESS_TOKENMastodon access token
X_API_KEYX (Twitter) API Key
X_API_SECRETX (Twitter) API Secret
X_ACCESS_TOKENX (Twitter) Access Token
X_ACCESS_SECRETX (Twitter) Access Secret

Railway

VariablePurpose
BUMBLEBEE_ENTITYEntity name to run (e.g. canary)
BUMBLEBEE_RAILWAY_ROLEworker or api
PORTAPI listen port (default 8080)