Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OLLOS_HOMENoJobs, cache, models~/.ollos
OLLOS_YTDLPNoExplicit binary path for yt-dlpauto
OLLOS_FFMPEGNoExplicit binary path for ffmpegauto
OLLOS_FFPROBENoExplicit binary path for ffprobeauto
OLLOS_OFFLINENo1 forbids network; models must be warmed up0
OLLOS_DEBUG_MEMNo1 stamps every job event with process memory (rss, heap, arrayBuffers in MB)0
OLLOS_MAX_FRAMESNoHard cap on frames per keyframes job500
OLLOS_YTDLP_ARGSNoExtra yt-dlp flags for every site download, allow-listed (e.g. --no-check-certificates --js-runtimes node)
OLLOS_ALLOW_PRIVATENoAllow fetching from private networks0
OLLOS_CONCURRENCY_OCRNoParallel jobs per class (ASR is fixed at 1)2
OLLOS_MAX_DOWNLOAD_MBNoDownload cap2048
OLLOS_RESPONSE_TOKENSNoResponse budget before truncation with a pointer to the resource20000
OLLOS_MAX_DURATION_SECNoMedia longer than this is refused (use from/to)14400
OLLOS_CONCURRENCY_VISIONNoParallel jobs per class (ASR is fixed at 1)2
OLLOS_CONCURRENCY_DOWNLOADNoParallel jobs per class (ASR is fixed at 1)2
OLLOS_INLINE_THRESHOLD_SECNoEstimated work under this runs inline; 0 never inlines8

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