Applying the ideas of Deepseek R1 to computer use

Janus-Series: Unified Multimodal Understanding and Generation Models

Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

an open-source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

[CVPR24] MaGGIe: Mask Guided Gradual Human Instance Matting

A simple open-source chat app that uses Exa's API for web search and Deepseek R1 for reasoning

Run AI Agent in your browser.

A database of SDKs, frameworks, libraries, and tools for creating, monitoring, debugging and deploying autonomous AI agents

Enable AI models for video production in the browser

A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.

List of projects that provide terminal user interfaces

Open Source realtime backend in 1 file

Compile Time Regular Expression in C++

A refreshingly simple data-driven game engine built in Rust

Learning how to write "Less Slow" code in C++ 20, C 99, CUDA, PTX, & Assembly, from numerics & SIMD to coroutines, ranges, exception handling, networking and user-space IO

An Open-Source Machine Learning Framework in Rust Δ

FastVideo is a lightweight framework for accelerating large video diffusion models.

Code for ExploreTom

Visual Studio Code

Vim-fork focused on extensibility and usability

Python tool for converting files and office documents to Markdown.

Official comfyui repository of Hellomeme

InspireMusic: A Unified Framework for Music, Song, Audio Generation.

Admin Dashboard UI built with Shadcn and Vite.

PanoDreamer: 3D Panorama Synthesis from a Single Image

The official implement of "FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression"

Jai is a programming language

30 C Compiler