Fast Model2Vec inference for potion-base-8M embeddings without ONNX or heavy ML frameworks
Fast Model2Vec inference for potion-base-32M embeddings without ONNX or heavy ML frameworks
ELID with text and image embedding models (Model2Vec + MobileNetV3)
ELID with text embedding models (Model2Vec potion-base-8M)
Content Extraction & Semantic Classification Library
Sivru search engine — gitignore-aware walker, code-aware chunker, BM25, cosine top-k, ranking signals, on-disk cache.
TypeScript interface schemas + JSON Schema definitions for SuperInstance fleet types
Semantic search and document parsing tools for the command line (Rust-backed, npm-distributed)
Semantic search and document parsing tools for the command line (Rust-backed, npm-distributed)
H2CO3's & Narnium's Rust Implementation of Model2Vec
Official Rust Implementation of Model2Vec
Model2Vec embedding module for vecgraph
Embedder implementations for frankensearch (hash, model2vec, fastembed)
Semantic code search CLI — like ripgrep but for meaning
Semantic code + document search engine. Cacheless static-embedding + cross-encoder rerank by default; optional ModernBERT/BGE transformer engines with GPU backends. Tree-sitter chunking, hybrid BM25 + PageRank, composable ranking layers.
MCP + LSP server for ripvec — semantic code search, PageRank repo maps, and multi-language code intelligence
Embedding engines (Model2Vec static + BERT via Candle + static-hash fallback) and HNSW vector database for post-cortex. Self-contained ML stack — depend on this crate when you need vector search without the full post-cortex orchestrator.
Fast and efficient vector graph database built on top of kvwrap.
Project memory for coding agents. Single binary, hybrid search, knowledge graph.
Blazingly fast word embeddings with Tokenlearn
SemanticFileFinder (sff): Fast semantic file finder using sentence embeddings. Searches .txt, .md, .mdx files.