safetensors

π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.

A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.

YC (S26) | AI that knows what you've seen, said, or heard. Records everything you do, say, hear 24/7, local, private, secure

Minimalist ML framework for Rust

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

Fast, flexible LLM inference

Spin is the open source developer tool for building and running serverless applications powered by WebAssembly.

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

Rust bindings for the C++ api of PyTorch.

3D Reconstruction for all

A blazing fast inference solution for text embeddings models

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

Inference at the speed of light.

NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.

Rust library for generating vector embeddings, reranking locally!

rvLLM: High-performance LLM inference in Rust. Drop-in vLLM replacement.

Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.

Pure Rust + CUDA LLM inference engine

Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

Pure Rust Inference Engine

MLX-based experimental inference engine

Build apps powered by on-device AI

Voice AI runtime. Local first transcription, speaker diarization, TTS, and voice cloning with an OpenAI compatible API.

ONNX neural network inference engine

Rust MCP server for multi-agent coordination: 34 tools, Git-backed archive, SQLite indexing, advisory file locks, and an interactive TUI console

A Rust-based AI agent orchestrator with Neo4j knowledge graph, Meilisearch semantic search, and Tree-sitter code parsing.

HyprStream: agentic infrastructure for continous online-learning applications

Next Generation Machine Learning, Statistics and Deep Learning in PURE Rust

A machine learning library for Python and Rust, for PyTorch, Tensorflow and SKLearn models

Terminal hypervisor for AI agent swarms: real-time pane capture, state-machine pattern detection, and a JSON API for coordinating fleets of coding agents across WezTerm

High Performance Low-Latency Frameworks

Two-tier hybrid search for Rust: sub-millisecond initial results via potion-128M, quality-refined rankings in 150ms via MiniLM-L6-v2. Combines lexical (Tantivy BM25) and semantic (vector cosine) search with Reciprocal Rank Fusion. Progressive iterator API, f16 SIMD vector index, feature-gated compilation.

Expert Kit is an efficient foundation of Expert Parallelism (EP) for MoE model Inference on heterogenous hardware

rust recursive deep learning framework

Local STT server powered by GigaAM v3.

Local AI image generation CLI — FLUX, SD 1.5, SDXL & Z-Image diffusion models on your GPU

pure rust inference engine

Multi-provider AI agent CLI written in Rust

Make Whisper work with APR model format and run in WASM

sparse ternary AI stack enabling efficient frontier intelligence without hyperscaler-scale infrastructure.

Decentralized AI Infrastructure