Skip to main content
Glama
fakehuman

fakehuman

Official
by idiap

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HF_HOMENoOverrides the normal Hugging Face cache location.
LLM_API_KEYNoAPI key for the configured LLM provider. It may be supplied through the environment, a secret manager, or a .env file.
HF_HUB_CACHENoOverrides the Hugging Face Hub cache location.
LLM_BASE_URLNoBase URL of the OpenAI-compatible LLM provider, including /v1 if required.
XDG_STATE_HOMENoBase state directory respected for the default run storage location.
FAKEHUMAN_RUNS_DIRNoOverrides the default directory where saved run reports are stored.
FAKEHUMAN_EDITOR_MODELNoOverrides the default editor model used for LLM rewriting.
FAKEHUMAN_REVIEWER_MODELNoOverrides the default reviewer model used for LLM rewriting.

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