Github Projects
OmniParser
2025-03-03
OmniParser is a versatile tool for extracting structured information from various document formats using advanced machine learning techniques.
Wan2.1
2025-03-01
Wan2.1 is a comprehensive suite of video foundation models that push the boundaries of video generation with SOTA performance and support for consumer-grade GPUs.
MarkItDown
2025-02-28
A powerful tool for converting and enhancing markdown files with advanced features.
Step-Video-T2V
2025-02-26
Step-Video-T2V is an AI-powered tool that converts text descriptions into dynamic videos, offering a seamless way to create visual content from written prompts.
Browser Use
2025-02-21
A collection of utilities and extensions designed to improve browser functionality and user experience.
Awesome DeepSeek Integration
2025-02-19
A curated list of tools, libraries, and resources for integrating DeepSeek AI into your projects.
Unsloth
2025-02-16
Unsloth is a tool designed to accelerate the fine-tuning process of machine learning models, enhancing performance without sacrificing accuracy.
Data Formulator
2025-02-13
A Microsoft open-source tool for transforming and visualizing data efficiently.
KTransformers
2025-02-09
KTransformers enhances transformer models by implementing efficient KV caching, reducing computational overhead and improving performance.
Qwen2.5-VL
2025-02-04
Qwen2.5-VL is an advanced vision-language model designed for seamless understanding and generation across visual and textual data.
Janus
2025-01-28
Janus is a cutting-edge multimodal AI model designed to integrate and process diverse data types for advanced AI applications.
Oumi AI
2025-01-26
Oumi AI is a cutting-edge platform designed to integrate and scale AI solutions effortlessly, providing robust tools for developers and enterprises.
RealtimeSTT
2025-01-24
A real-time speech-to-text (STT) solution designed for low-latency voice interaction applications.
DeepSeek-R1
2025-01-23
DeepSeek-R1 is an open-source project offering high-performance language models designed for efficiency and scalability.
Cosmos
2025-01-21
Cosmos is a GPU-accelerated library for high-performance computing and scientific simulations.
Monolith
2025-01-18
Monolith is a deep learning framework designed for large-scale recommendation systems, featuring collisionless embedding tables and real-time training.
Sana
2025-01-16
Sana is an AI-powered platform for advanced medical imaging analysis, developed by NVlabs to enhance diagnostic accuracy and efficiency.
WrenAI
2025-01-14
WrenAI enables users to explore and analyze data through natural language queries, powered by AI.
MiniPerplx
2025-01-08
MiniPerplx is a lightweight interpreter for a dynamically-typed programming language, designed for educational and scripting purposes.
Siyuan
2025-01-06
Siyuan is a local-first, privacy-focused knowledge management system that supports Markdown, block references, and bidirectional linking.
DeepSeek-V3
2025-01-04
DeepSeek-V3 is a cutting-edge AI language model designed for advanced natural language processing tasks.