Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
SESSION_RAG_HOMENoDirectory for the index, models, and logs. Default: ~/.local/share/session-rag.
CLAUDE_CONFIG_DIRNoDirectory where Claude Code transcripts are read from. Default: ~/.claude.
SESSION_RAG_MODELNoFastembed text model to use. Default: minishlab/potion-multilingual-128M. Reindex with --rebuild when changing.
CLAUDE_PROJECT_DIRNoDirectory used to select the current project; the server otherwise uses the working directory.
SESSION_RAG_THREADSNoNumber of threads for the shared server model, which is loaded once and limited to two threads.
SESSION_RAG_RERANKERNoCross-encoder model used by session-rag search --precise. Default: jinaai/jina-reranker-v2-base-multilingual.
SESSION_RAG_IDLE_UNLOADNoSeconds without calls before the shared server unloads the model; 0 keeps it loaded.
SESSION_RAG_NO_USAGE_LOGNoIf set, disables the local usage log.

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