Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoListen address.0.0.0.0
PORTNoListen port.8000
HF_HOMENoDirectory where model weights are cached.
BASE_URLNoPublic URL of the server, required in github mode.
DATA_DIRNoDirectory for OAuth state and persisted data (default /data in Docker)../data
AUTH_MODENoAuthentication mode: none, bearer, or github (default: bearer).bearer
LOG_LEVELNoLogging level.INFO
MAX_ITEMSNoMaximum items per batch call.50
API_TOKENSNoComma-separated bearer tokens used for authentication in bearer mode.
APP_SECRETNoSigns tokens and encrypts OAuth state. Keep it stable.
LOW_CONFIDENCENoAnswers below this confidence are reported in low_confidence.0.7
OMP_NUM_THREADSNoCPU threads for inference.
CALIBRATION_PATHNoPath to a JSON file with temperatures for calibration.
GITHUB_CLIENT_IDNoGitHub OAuth App client ID for github authentication mode.
LAYA_CHECKPOINTSNoComma separated list: multilingual, english, typed-decisions. Use multilingual for non-English.multilingual
ALLOWED_GITHUB_USERSNoGitHub usernames allowed to use the tools (comma separated).
GITHUB_CLIENT_SECRETNoGitHub OAuth App client secret for github authentication mode.
LOW_CONFIDENCE_FIELDNoField used when no calibration is loaded: answer_confidence or the stricter confidence.answer_confidence

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources