Super-Memory-TS
by Veedubin
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| QDRANT_URL | No | Qdrant server URL | http://localhost:6333 |
| BOOMERANG_DEVICE | No | Compute device: auto, gpu, cpu | auto |
| BOOMERANG_USE_GPU | No | Enable GPU usage | false |
| QUERY_COLLECTIONS | No | Comma-separated list of collections to search (for multi-collection RRF) | |
| BOOMERANG_LOG_LEVEL | No | Log level: debug, info, warn, error | info |
| BOOMERANG_PRECISION | No | Model precision: fp32, fp16, q8, q4 | fp32 |
| BOOMERANG_CHUNK_SIZE | No | Token chunk size for indexing | 512 |
| BOOMERANG_PROJECT_ID | No | Project identifier for memory isolation | |
| BOOMERANG_CHUNK_OVERLAP | No | Overlap between chunks | 50 |
| BOOMERANG_MAX_FILE_SIZE | No | Max file size (bytes) to index | 10485760 |
| SUPER_MEMORY_EAGER_LOAD | No | Set to 1 to preload the model at startup | |
| BOOMERANG_SEARCH_STRATEGY | No | Default search strategy: tiered, parallel | tiered |
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
ActivityInactive
ResponsivenessNo issues