Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MEM0_MODELNoLLM model for cognitive features.
MEMENTO_UINoEnable local web UI ('1'/'true').
MEMENTO_DIRNoWorkspace root for .memento/ state.
OPENAI_API_KEYNoRequired for embeddings and cognitive features if not using offline mode.
MEMENTO_UI_PORTNoLocal UI port (default '8089').
OPENAI_BASE_URLNoOptional OpenAI-compatible endpoint (e.g. OpenRouter).
MEM0_EMBEDDING_MODELNoEmbeddings model for hybrid search.
MEMENTO_EMBEDDING_BACKENDNoSet to 'none' for FTS5-only (no API key needed).
MEMENTO_HANDOFF_AUTO_CHECKPOINT_EVERY_N_EVENTSNoAuto-checkpoint frequency (default '25').

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/JoyciAkira/memento'

If you have feedback or need assistance with the MCP directory API, please join our Discord server