Acknowledgements

Credits and citations

Embedding model

The default embedding model used by VecGrep is all-MiniLM-L6-v2-code-search-512, a model fine-tuned specifically for semantic code search by @isuruwijesiri.

@misc{all_MiniLM_L6_v2_code_search_512,
  author    = {isuruwijesiri},
  title     = {all-MiniLM-L6-v2-code-search-512},
  year      = {2026},
  publisher = {Hugging Face},
  url       = {https://huggingface.co/isuruwijesiri/all-MiniLM-L6-v2-code-search-512}
}

Libraries

• fastembed — ONNX Runtime-based embedding (default backend)
• sentence-transformers — PyTorch embedding backend
• LanceDB — vector store
• tree-sitter — AST-based code chunking
• MCP — Model Context Protocol