Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MEMORY_DBNoPath to the SQLite database file.
MEMORY_ROOTNoRoot data directory.
MEMORY_TOKENNoAccess token for the API. Leave empty to disable authentication; set it when exposed externally.
AFFECT_WAKE_TOKENNoToken for the affect/wake subsystem. Leave empty to disable authentication; set it when exposed externally.
MEMORY_VECTOR_URLNoOptional Qdrant vector index URL. Leave empty to disable the vector index.
MEMORY_ARCHIVE_DIRNoPath to the archive directory.
MEMORY_MODEL_API_KEYYesAPI key for the OpenAI-compatible model endpoint (required for model-dependent features).
MEMORY_MODEL_BASE_URLYesOpenAI-compatible model endpoint URL (required for model-dependent features).
MEMORY_CONTINUITY_REVIEW_TOKENNoToken for continuity review. Leave empty to disable authentication; set it when exposed externally.

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