CodeSift
by greglas75
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CODESIFT_DATA_DIR | No | Storage directory for indexes | ~/.codesift |
| CODESIFT_OLLAMA_URL | No | Ollama URL for local embeddings (optional) | |
| CODESIFT_LOCAL_MODEL | No | Override local embedding model (e.g., 'Xenova/bge-small-en-v1.5') | |
| CODESIFT_SECRET_SCAN | No | Enable/disable secret scanning (set 'false' to disable) | true |
| CODESIFT_DEFAULT_TOP_K | No | Default max results for search | 50 |
| CODESIFT_OPENAI_API_KEY | No | OpenAI API key for semantic search (optional) | |
| CODESIFT_VOYAGE_API_KEY | No | Voyage AI API key for semantic search (optional) | |
| CODESIFT_WATCH_DEBOUNCE_MS | No | File watcher debounce interval | 500 |
| CODESIFT_DEFAULT_TOKEN_BUDGET | No | Default token budget for retrieval | 8000 |
| CODESIFT_EMBEDDING_BATCH_SIZE | No | Symbols per embedding API call | 128 |
| CODESIFT_MAX_EMBEDDING_MEM_MB | No | Cap resident embedding RAM in MB | 1024 |
| CODESIFT_DISABLE_LOCAL_EMBEDDINGS | No | Set to 'true' to disable local embeddings (Lite mode) |
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
ResponsivenessUnresponsive