Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
KANERVA_HOMENoWhere the database lives.~/.kanerva
KANERVA_LEARNNoSet to `1` to learn from which notes were used. Default: off.
KANERVA_EMBEDDERNoSet to `static` to add vector search with model2vec. Good for long conversational notes, worse for exact code facts. Downloads a small model on first use. Default: off.
KANERVA_MIN_WEIGHTNoSkip notes below this estimated probability of being needed.0.02
KANERVA_CONSOLIDATENoSet to `1` to merge near-duplicate notes on compaction. Merges can be undone. Default: off.
KANERVA_PROMPT_BUDGETNoTokens injected per prompt.600
KANERVA_SESSION_BUDGETNoTokens injected at session start.400

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