Memorised them All
by GRU953
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MTA_HOME | No | Where memory is stored | ~/.memorised-them-all |
| MTA_BACKEND | No | Use another local model server | auto |
| MTA_PROFILE | No | Sizing tier: micro (4 GB / no-GPU — the safe default) · auto · small · standard (16 GB) · large (32 GB+) · offline | micro |
| MTA_OCR_LANG | No | OCR languages (Tesseract codes; missing packs dropped automatically) | eng+ben |
| MTA_MEMORY_GB | No | Override detected RAM | auto |
| MTA_NO_OLLAMA | No | Force fully-offline mode (no AI model) | |
| MTA_AUTO_UPDATE | No | Daily update check (off to disable) | on |
| MTA_BACKEND_URL | No | URL for the backend server | |
| MTA_EMBED_MODEL | No | Multilingual embeddings (1024-d, incl. Bangla) | qwen3-embedding:0.6b |
| MTA_VISION_MODEL | No | Image caption / OCR-assist (32-language) | qwen3-vl:4b-instruct |
| MTA_BANGLA_LEGACY | No | Enable legacy Bengali conversion (off to disable) | on |
| MTA_EXTRACT_MODEL | No | Extraction LLM — overrides the profile | (set by profile) |
| MTA_WHISPER_MODEL | No | On-device speech-to-text size | small |
| MTA_CONVERT_TIMEOUT | No | Per-file conversion timeout (seconds); 0 disables | 120 |
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
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityStale
ResponsivenessNo issues