Build software better, together

huggingface / transformers

🤗 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.

audio python nlp machine-learning natural-language-processing deep-learning pytorch transformer speech-recognition glm pretrained-models hacktoberfest gemma vlm pytorch-transformers model-hub llm qwen deepseek

Updated Nov 11, 2026
Python

bytedance / UI-TARS-desktop

Star

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

agent mcp vision vlm tars multimodal cowork computer-use mcp-server gui-agent browser-use gui-operator ui-tars agent-tars

Updated Oct 9, 2026
TypeScript

sgl-project / sglang

Star

SGLang is a high-performance serving framework for large language models and multimodal models.

reinforcement-learning cuda inference transformer moe attention llama glm minimax wan diffusion vlm blackwell llm qwen deepseek gpt-oss qwen-image

Updated Nov 11, 2026
Python

StarTrail-org / PixelRAG

Star

https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

search agent ai memory vision vlm searchengine multimodal rag

Updated Nov 11, 2026
Python

RunanywhereAI / runanywhere-sdks

Star

Production ready toolkit to run AI locally

Updated Nov 10, 2026
C++

A collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL.

Updated Sep 22, 2026
Jupyter Notebook

yzhao062 / anomaly-detection-resources

Sponsor

Star

Anomaly detection related books, papers, videos, and toolboxes. Last update late 2025 for LLM and VLM works!

machine-learning data-mining awesome awesome-list outlier-detection unsupervised-learning fraud-detection time-series-analysis vlm anomaly-detection fraud outlier outlier-ensembles graph-neural-networks large-language-models llm vlms

Updated Mar 2, 2026
Python

oumi-ai / oumi

Star

Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!

Updated Nov 10, 2026
Python

qualcomm / GenieX

Star

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

go sdk hexagon snapdragon qualcomm vlm on-device-ai llm local-ai llama3 qwen3 gpt-oss granite4 qwen3vl gemma4

Updated Nov 11, 2026
Go

PaddlePaddle / ERNIE

Star

The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.

vlm ernie llm erniekit ernie-45 ernie-45-vl

Updated Jul 24, 2026
Python

JuneYaooo / rea-video

Star

Reverse-engineer any video, shot by shot: filmed, AI-generated or coded, and how to remake it. 逆向一切视频，逐个镜头看是拍的、AI 生成的还是代码做的，再告诉你怎么复刻。

ffmpeg reverse-engineering subtitles video-editing codex vlm video-analysis short-video video-generation shot-detection remotion prompt-engineering ai-video aigc-detection agent-skills claude-code video-breakdown

Updated Nov 10, 2026
Python

om-ai-lab / VLM-R1

Star

Solve Visual Understanding with Reinforced VLMs

reinforcement-learning vlm multimodal llm qwen deepseek-r1 grpo r1-zero vlm-r1 multimodal-r1

Updated Jul 7, 2026
Python

OpenBMB / UltraRAG

Star

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

flask demo ui mcp openai easy gpt embedding vlm multimodal rag sentence-transformers huggingface-transformers llm vllm qwen deepseek

Updated Nov 9, 2026
Python

changyeyu / LLM-RL-Visualized

Star

🌟100+ 原创 LLM / RL 原理图📚，《大模型算法》作者巨献！💥（100+ LLM/RL Algorithm Maps ）

machine-learning natural-language-processing algorithm reinforcement-learning ai deep-learning transformers nlp-machine-learning vlm llm

Updated Sep 10, 2026
Python

joanrod / star-vector

Star

StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and textual inputs to produce high-quality SVG code with remarkable precision.

svg vlm llm multimodal-large-language-models