Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
RAG_DIRNoWhere rag.db lives.~/.wetnoodle
RAG_HYBRIDNoKeyword rerank inside vector candidates.1
RAG_OLLAMANoOllama daemon URL.http://127.0.0.1:11434
RAG_PER_CORPUSNoPer-corpus slot quotas — measured worse, off.0
RAG_VEC_WEIGHTNoVector share of the rerank blend.0.7
RAG_EMBED_MODELNoPins vector dim; changing it requires ingest.py --full.nomic-embed-text
RAG_HERMES_HOMENoHermes install to index.~/.hermes
RAG_SKILLS_DIRSNoOverride skill roots (colon-separated).discovered
RAG_MAX_HIT_CHARSNoPer-hit cap in tool output.800
RAG_MAX_TOTAL_CHARSNoCap across the whole result set.6000

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