Skip to main content
Glama
GRU-953

Memorised them All

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MTA_HOMENoWhere memory is stored~/.memorised-them-all
MTA_BACKENDNoUse another local model serverauto
MTA_PROFILENoSizing tier: micro (4 GB / no-GPU — the safe default) · auto · small · standard (16 GB) · large (32 GB+) · offlinemicro
MTA_OCR_LANGNoOCR languages (Tesseract codes; missing packs dropped automatically)eng+ben
MTA_MEMORY_GBNoOverride detected RAMauto
MTA_NO_OLLAMANoForce fully-offline mode (no AI model)
MTA_AUTO_UPDATENoDaily update check (off to disable)on
MTA_BACKEND_URLNoURL for the backend server
MTA_EMBED_MODELNoMultilingual embeddings (1024-d, incl. Bangla)qwen3-embedding:0.6b
MTA_VISION_MODELNoImage caption / OCR-assist (32-language)qwen3-vl:4b-instruct
MTA_BANGLA_LEGACYNoEnable legacy Bengali conversion (off to disable)on
MTA_EXTRACT_MODELNoExtraction LLM — overrides the profile(set by profile)
MTA_WHISPER_MODELNoOn-device speech-to-text sizesmall
MTA_CONVERT_TIMEOUTNoPer-file conversion timeout (seconds); 0 disables120

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/GRU-953/memorised-them-all'

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