Stars
A command-line interface for local translation powered by plamo-3-translate, a PFN™ translation model
A bilingual reference studio for poses, costumes, and AI character creation.
Interactive 3D simulator of Leibniz's stepped reckoner, the first mechanical calculator to add, subtract, multiply and divide. Lessons in 10 languages, in the browser.
Multimodal OCR: Parse Anything from Documents
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.
Gemma open-weight LLM library, from Google DeepMind
Everything about the SmolLM and SmolVLM family of models
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Fast and local neural text-to-speech engine
A TTS that fits in your CPU (and pocket)
Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces
Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.
Modular battery-powered touch remote for Home Assistant, built with ESPHome and LVGL on a Freenove ESP32-S3 2.8" display. Pick your pages (lights, LED, Apple TV, appliances, power) and add as many …
An on-device AI agent for Android that operates apps and the web to get things done for you.
⚡️A native, local-first alternative to Logitech Options+, written in Rust 🦀 — remap buttons, DPI, and SmartShift over HID++. No account, no telemetry.
All your computers and your phone/iPhone, working as one desk. Screens, apps, files, clipboard, calls, texts, notifications, mouse and keyboard, shared between Mac, Windows, Linux , Android, Web a…