rust

Privacy-first voice-to-text for macOS and Windows. Local Whisper (Metal/CUDA) or Groq cloud, with LLM post-processing. Built with Rust + Tauri 2.

Minimalist voice-to-text app. Hold hotkey, speak, auto-paste. Cloud transcription via OpenAI/Groq.

Rust server that summarizes text with pre-trained models

🎤 游戏玩家的 Windows 桌面语音输入工具 — 按住热键说话，本地流式转写，松开一键发送到游戏聊天框。Tauri 2 + Rust + sherpa-onnx，识别全程本机完成。

Fast, privacy-first voice typing with streaming transcription and BYOK. 快速、隐私优先的流式语音输入工具，支持自带 API Key。

A thread-safe vector database for model inference inside LMDB.

Scala bindings for Hugging Face Tokenizers

A vector database for querying meaningfully similar data.

KoutenDB: locality-aware NoSQL document/vector database built around rings and orbit-inspired retrieval

Embeddable vector database for Rust and Python. HNSW indexing, metadata filtering, hybrid search, and snapshots. The SQLite of vector search.

The in-browser vector store that remembers — a Rust→WASM HNSW engine that persists to OPFS and stays consistent across tabs. Private, offline semantic search in 3 lines.

This tool provides a fast and efficient way to convert text into vector embeddings and store them in the Qdrant search engine. Built with Rust, this tool is designed to handle large datasets and deliver lightning-fast search results.

CLI tool for OpenAI compatible APIs

Verified multi-source distribution for local LLM weights

Harvest-first Rust toolkit for open data metadata: sync 300+ portals (CKAN, DCAT, SPARQL, data.json, Socrata, OpenDataSoft, ArcGIS, CSW, STAC ) into PostgreSQL, add optional local embeddings and semantic search. Ceres Open Data Index (2M+ datasets) on Hugging Face.

vector database built on top of S3, inspired by turbopuffer

The data layer for AI with Vector, Graph and Vector-Math built into one single rust engine

chew through any source into clean datasets! a fast ingestion, RAG & fine-tuning toolkit

Local AI model manager

Deterministic context database for AI agents. Same query → same context, every time.