exomem
by Artexis10
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EXOMEM_MODE | No | Hard-pin resource mode: `quiet`, `normal`, or `performance`. Env wins over config. | |
| EXOMEM_DEVICE | No | Force all torch models to `cuda`, `mps`, or `cpu`. Normally leave unset and use `exomem mode`. | |
| EXOMEM_BASE_URL | No | Base URL for the MCP server, if using a remote service. | |
| EXOMEM_MPS_FP16 | No | On Apple Silicon, run bge/CLIP in fp16 on the Metal GPU — ~half the memory, faster encodes (default on; set `0` to keep fp32). | |
| EXOMEM_AUTO_QUIET | No | `1` enables optional non-torch GPU-pressure auto-quiet switching (default off). | |
| EXOMEM_KB_DIRNAME | No | Name of the governed folder inside the vault (default `Knowledge Base`). | |
| EXOMEM_QUIET_MODE | No | Legacy truthy alias for `quiet` when `EXOMEM_MODE` is unset. | |
| EXOMEM_VAULT_PATH | Yes | Vault root containing the governed folder (default `Knowledge Base/`). | |
| EXOMEM_ASR_BACKEND | No | ASR engine: `mlx` (Apple Silicon Metal GPU, needs the `media-mlx` extra) or `faster-whisper` (CUDA/CPU). Default auto-selects MLX on Apple Silicon, else faster-whisper. | |
| EXOMEM_DISABLE_CLIP | No | `1` disables CLIP image search. | |
| EXOMEM_REST_API_KEY | No | Enables authenticated REST routes. | |
| EXOMEM_TORCH_DEVICE | No | Force all torch models to `cuda`, `mps`, or `cpu`. Normally leave unset and use `exomem mode`. | |
| EXOMEM_DISABLE_TIER2 | No | `1` hides Tier-2 filesystem tools. | |
| EXOMEM_TESSERACT_CMD | No | Path to the `tesseract` binary if not auto-discovered. | |
| EXOMEM_WHISPER_MODEL | No | faster-whisper model size for ASR, such as `base` or `small`. | |
| EXOMEM_MLX_WHISPER_MODEL | No | HF repo for the MLX ASR model (default `mlx-community/whisper-large-v3-mlx`; use `mlx-community/whisper-large-v3-turbo` for speed). | |
| EXOMEM_SEMANTIC_SEGMENTS | No | Set to enable timed transcripts + semantic segment retrieval for audio/video (default off). | |
| EXOMEM_DISABLE_EMBEDDINGS | No | `1` forces keyword/BM25-only search. | |
| EXOMEM_VIDEO_SCENE_FRAMES | No | Set to enable video scene detection + persisted, OCR'd scene-frame JPEGs (default off). | |
| EXOMEM_VIDEO_SCENE_MIN_SECS | No | Minimum scene duration in seconds; closer boundaries merge (default 4). | |
| EXOMEM_VIDEO_SCENE_THRESHOLD | No | Scene-boundary hash threshold in bits of 64 (default 10). | |
| EXOMEM_DISABLE_MEDIA_EXTRACTION | No | `1` skips server-side OCR/ASR/PDF/Office extraction. |
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
ActivityActive
ResponsivenessResponsive