Photon – Rust pipeline that embeds/tags/hashes images locally w SigLIP
Local SigLIP embeddings + 68K-term semantic tagging in a single Rust binary, zero cloud.
Rust library for generating vector embeddings, reranking locally!
Rust port of Qdrant's fastembed when the Python original already works fine.
Rust developers building RAG pipelines or semantic search features
Qdrant fastembed · Sentence Transformers · Cohere Embed
Local SigLIP embeddings + 68K-term semantic tagging in a single Rust binary, zero cloud.
Replaces Windows Search with vector + full-text hybrid; EXIF geocoding and function-level code chunking actually work.
Local-first agent memory with SQLite graphs, but requires a license key.
Using a single-file .pardus format with CREATE/INSERT/SELECT + SIMILARITY queries gives a very familiar developer UX for embedding storage. The combination of graph-based ANN, full transactions, thread-safety, and zero external dependencies is an uncommon and useful engineering combo for local-first AI work; it would win more attention with benchmark comparisons and richer ecosystem integrations (connectors/clients).
Manually converting PyTorch models to CoreML so you don't have to call cloud APIs.
Embedding auditor with 5 checks and pretty plots, but crowded niche with unclear novelty.