Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

RuVector is a High Performance, Real-Time, Self-Learning Ai, Vector GNN, Memory DB built in Rust.

Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

Fast ML inference & training for ONNX models in Rust

A WebGPU-accelerated ONNX inference run-time written 100% in Rust, ready for native and the web

Cognitive memory for AI agents — FSRS-6 spaced repetition, 29 brain modules, 3D dashboard, single 22MB Rust binary. MCP server for Claude, Cursor, VS Code, Xcode, JetBrains.

Confidential AI deployment with secure enclaves 🔒

A Rust library integrated with ONNXRuntime, providing a collection of Computer Vison and Vision-Language models such as YOLO, FastVLM, and more.

AI-powered desktop app for stunning image transformations

A work in progress to build out solutions in Rust for MLOPs

Anything — 파일을 찾지 말고, 내용을 찾으세요. HWPX · PDF · Office 수천 건의 본문을 1초 만에. 100% 로컬 · 완전 오프라인 · AI Q&A 옵션 (Tauri · React · Rust) | Local content search for Korean PCs — HWP-first, fully offline

Rust wrapper for Microsoft's ONNX Runtime (version 1.8)

ONNX neural network inference engine

very fast speech-to-text, diarization, streaming (even in CPU) with NVIDIA Parakeet in Rust

Knowledge Management for Humans and Agents

A DuckDB extension for in-database inference

Distribute and run transformer encoders with a single file.

Small ONNX inference runtime written in Rust

Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ranges, and symbol metadata. Built in Rust.

Real time, privacy first, low latency push to talk using Parakeet fully on device with Tauri and ORT.