Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
ADMIN_TOKENNoOptional: shelving tours on the poster wall and the benchmark (scripts/bench.mjs)
QLOO_API_KEYYesEvery Qloo call (hackathon host https://hackathon.api.qloo.com, header X-Api-Key)
QLOO_BASE_URLNoOptional, defaults to the hackathon host
NEBIUS_API_KEYNoThe agent, the control group and the pitches. Without it, the fixed plan and template pitches run
TAVILY_API_KEYNoOptional: room capacities use Tavily's keyless mode by default; set TAVILY_USE_KEY=1 to search with this key instead
TAVILY_USE_KEYNoSet to 1 to search with TAVILY_API_KEY instead of keyless mode
DAILY_MODEL_CAPNoModel runs per day for the public demo (default 200; the live site uses 50)
BLOB_READ_WRITE_TOKENNoVercel Blob for tours and the capacity cache. Without it, tours are files under .data/

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