Skip to main content
Glama
nikships
by nikships

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GEMDEX_MODENoSelect the embedded 'local' backend or a configured 'remote' backendlocal
HYBRID_MODENoDisable to use dense-only recalltrue
LANCEDB_PATHNoFilesystem path for the embedded memory store~/.gemdex/lance
GEMINI_API_KEYNoGoogle AI Studio API key (needed to embed on save/recall/update). Set to 'local' to use MLX text embeddings.
EMBEDDING_MODELNoOverride Gemini embedding modelgemini-embedding-2
GEMINI_BASE_URLNoCustom Gemini endpoint
GEMDEX_REMOTE_URLNoGemdex Server root URL
GEMDEX_SERVE_PORTNoDefault port for gemdex serve0
GEMDEX_STATS_PATHNoWhere the report_outcome feedback ledger is stored~/.gemdex/stats.json
EMBEDDING_DIMENSIONNoForce Matryoshka-resized dimension (256/768/1536/3072)
GEMDEX_REMOTE_TOKENNoGemdex Server bearer token
GEMDEX_TRUST_RANKINGNoSet 'true' to re-rank recall results by track recordfalse
GEMDEX_SIMILAR_ON_SAVENoSet 'false' to disable save-time similar-memory detectiontrue
GEMDEX_SIMILAR_THRESHOLDNoCentroid cosine-similarity bar for save-time detection0.90

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