Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
SVGLOOP_MODELYesModel name, used for drawing and reviewing. Must be one your server knows.
SVGLOOP_CONFIGNoPath to a config file.
SVGLOOP_API_KEYNoOptional bearer key.
SVGLOOP_OUT_DIRNoWhere results go. Default: ~/SVGLoop (or out/ next to a config file).
SVGLOOP_BASE_URLYesOpenAI-compatible base URL, e.g. http://127.0.0.1:8080/v1.
SVGLOOP_EXTRA_BODYNoJSON merged into every request. For thinking models on llama.cpp: {"chat_template_kwargs":{"enable_thinking":false}}.
SVGLOOP_VISION_MODELNoOptional model name for the review step.
SVGLOOP_VISION_API_KEYNoOptional bearer key for the review model or server.
SVGLOOP_VISION_BASE_URLNoOptional base URL for using a different model or server for the review step.

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