onnx

Easy and fast 2d human and animal multi pose estimation using SOTA ViTPose [Y. Xu et al., 2022] Real-time performances and multiple skeletons supported.

Inference Stable Diffusion with C# and ONNX Runtime

🧠 The Brain for Your AI — Local-first memory engine for AI agents. Store, recall, and search memories with semantic embeddings. Single Rust binary, zero config, fully offline.

Python package to generate image embeddings with CLIP without PyTorch/TensorFlow

Real-time on-device text-to-image and image-to-image Semantic Search with video stream camera capture using USearch & UForm AI Swift SDKs for Apple devices 🍏

Your users download a 4GB AI model, the connection drops at 3.8GB, verifyfetch resumes from 3.8GB and verifies every byte. Drop-in integrity verification for Transformers.js, WebLLM, and any large file in the browser.

Easiest way of fine-tuning HuggingFace video classification models

Run local LLM from Huggingface in React-Native or Expo using onnxruntime.

ComfyUI Depth Anything (v1/v2/v3/distill-any-depth) Tensorrt Custom Node (up to 14x faster) ⚡

AudioMuse-AI Jellyfin Plugin enhances music discovery by using sonic analysis to queue similar songs in real time.

Accelerated NLP pipelines for fast inference on CPU. Built with Transformers and ONNX runtime.

Stable Diffusion UI: Diffusers (CUDA/ONNX)

Accelerated NLP pipelines for fast inference on CPU and GPU. Built with Transformers, Optimum and ONNX Runtime.

Deploy stable diffusion model with onnx/tenorrt + tritonserver

Speaker diarization for Python — "who spoke when?" CPU-only, no API keys, Apache 2.0. ~10.8% DER on VoxConverse, 8x faster than real-time.

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.

World's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated

An autonomous, context-aware AI desktop companion. Built with Python, featuring real-time screen vision, custom ONNX voice synthesis, active window tracking, and a dynamic floating UI with reactive facial expressions.

AI Speech Solutions for Tasks such as ASR, Vocal Extraction, Accompaniment Extraction, Audio Denoising, and Enhancement, Support models such as paraformer, sensevoice, fireredasr, zipformer, moonshine, wenet, whisper, fsmn-vad, silero-vad, CT Transformer punc, Spleeter, Uvr5, etc, apply ONNX models in various scenarios.

A local-first, high-performance desktop asset manager for AI image generations. Features universal metadata parsing (ComfyUI/A1111), instant SQLite search, visual duplicate detection, and offline AI auto-tagging.