Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoHTTP port.5000
HF_MIRRORNoEmbedding model download mirror.https://hf-mirror.com
CORS_ORIGINNoHTTP mode cross-origin whitelist.*
COGNITION_MODENoSet to 'local' for local fallback mode, or 'remote' to connect to the enhanced server. Defaults to 'remote'.remote
ANTHROPIC_API_KEYNoAnthropic API key (alternative for recognizer LLM configuration).
COGNITION_API_KEYNoRemote mode API key.
COGNITION_DATA_DIRNoData storage directory.~/.ai-cognition/
COGNITION_LLM_MODELNoRecognizer LLM model.deepseek-chat
COGNITION_RECOGNIZERNoSet to '1' to enable automatic memory recognition.0
COGNITION_SERVER_URLNoRemote algorithm server address (self-hosted). Must be explicitly configured when using remote mode.
COGNITION_LLM_API_KEYNoRecognizer LLM key (OpenAI compatible).
COGNITION_LLM_BASE_URLNoRecognizer LLM address.https://api.deepseek.com

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