Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MNEMOSYNENoPath to the mnemosyne binary, to pin a non-PATH binary when using the mnemosyne backend.
HEIMDALL_BACKENDNoSelects the retrieval/search backend. Graft is the zero-config default; set to "mnemosyne" to use mnemosyne-oss (SQLite-backed agent memory) as the retrieval backend. Resolution order: $HEIMDALL_BACKEND > ~/.heimdall/config.json `backend` key > graft. Can also be set persistently in ~/.heimdall/config.json.graft
HEIMDALL_NO_BUILDNoOpt out of auto-building the graft backend during install, e.g. HEIMDALL_NO_BUILD=1 npm i -g @arihantdeva/heimdall. When prerequisites are missing or this is set, the backend can be built later with `heimdall setup`.

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

Maintenance

ActivityActive
ResponsivenessNo issues