Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MEMSILO_CONFIGNoPath of the config file. If set, the file must exist.config.yaml
MEMSILO_DOTENVNoWhich .env file to read. An empty value disables loading../.env
OPENAI_API_KEYNoAPI key for the OpenAI-compatible endpoint; any non-empty value if the server needs none. Required when using the openai provider.
QDRANT_API_KEYYesQdrant API key. Required by the provided compose file, which sets the bundled Qdrant to require it. Empty means no key (only for a Qdrant of your own that needs none).
OPENAI_BASE_URLNoOpenAI-compatible endpoint, for example http://ollama-host:11434/v1. Required when using the openai provider.
ANTHROPIC_API_KEYNoLLM key; required when llm.provider is anthropic.
MEMSILO_LLM_MODELNoModel used to extract facts. Set a suitable model when using the openai provider.claude-haiku-4-5-20251001
MEMSILO_TELEMETRYNoMem0 anonymous usage telemetry. Off unless turned on.false
MEMSILO_TRANSPORTNoTransport: stdio, sse or streamable-http. Compose sets streamable-http.stdio
MEMSILO_COLLECTIONNoCollection that holds every customer's memories.memsilo
MEMSILO_HISTORY_DBNoMem0 SQLite history database path.data/history.db
MEMSILO_QDRANT_URLNoQdrant address. Compose sets http://qdrant:6333.http://localhost:6333
MEMSILO_USERS_FILENoToken store path.data/users.json
MEMSILO_SERVER_HOSTNoBind address for the HTTP transports. Compose sets 0.0.0.0.127.0.0.1
MEMSILO_SERVER_PORTNoPort (1-65535).8100
MEMSILO_LLM_PROVIDERNoMem0 LLM provider. Use openai for an OpenAI-compatible server.anthropic
MEMSILO_EMBEDDER_DIMSNoVector size; must match the embedding model.384
MEMSILO_EMBEDDER_MODELNoEmbedding model.BAAI/bge-small-en-v1.5
MEMSILO_DEFAULT_USER_IDNoUser the unauthenticated stdio transport acts as. Must be a valid user id.default
MEMSILO_EMBEDDER_PROVIDERNoEmbedding provider. Runs locally by default.fastembed

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