Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LTM_CHANNELNoHonker pub-sub channel.
LTM_DB_PATHNoWhere the SQLite file lives. Overrides the default location.
LTM_HONKER_EXTNoExplicit path to the Honker extension. Loads native code.
LTM_SQLITE_LIBNoExplicit path to a SQLite library. Loads native code.
LTM_DISABLE_VECNoTurn off the sqlite-vec loader; falls back to JS-cosine.
LTM_EMBED_MODELNoEmbedding model used by the local llama.cpp server. Default `bge-m3`.bge-m3
LTM_LLM_PROVIDERNoProvider for janitor summaries. Unset → `ollama` (local). Cloud providers (`anthropic`, `openai`, `gemini`, `cohere`, `openrouter`) are opt-in.
LTM_LLAMA_CPP_URLNoOptional override for the URL of the local llama.cpp embeddings server.
LTM_DISABLE_HONKERNoTurn off the Honker loader.
LTM_EMBED_PROVIDERNoEmbedding provider. Unset probes local llama.cpp (`llamacpp`); falls back to FTS if the server is down. `ollama` / `disabled` and the cloud providers (`openai`, `gemini`) opt in or out.
LTM_BACKUP_RETENTIONNoHow many rotated backups to keep.
LTM_JANITOR_ON_SESSION_ENDNo`0` disables the janitor-on-`SessionEnd` hook.
LTM_JANITOR_INTERVAL_MINUTESNoMinimum minutes between `janitor run --if-due` passes (hook, timers, daemon). Default 360.360

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