vlm repositories

Trending repositories tagged vlm, ranked by trending score. Updated daily.

  1. 1
    JuneYaooo/rea-video

    Reverse-engineer any video, shot by shot: filmed, AI-generated or coded, and how to remake it. Breakdowns in the open VIDEO.md format. 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;拆解结果按 VIDEO.md 格式输出。

    GitHub · Python · 11,402 stars · 1,693 forks · +791 stars in 24 hours · Trending score 5.67

  2. 2
    WayneChou-bot/WareTwin

    Real-time 3D digital twin of an autonomous warehouse — 20 AMRs, deterministic simulation, explainable fleet scheduling, failure injection, VLM camera perception, AI Ops Copilot and what-if scenarios. React Three Fiber + FastAPI.

    GitHub · TypeScript · 165 stars · 74 forks · +48 stars in 24 hours · Trending score 2.90

  3. 3
    SoMarkAI/OXR

    An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.

    GitHub · Python · 3,819 stars · 262 forks · +29 stars in 24 hours · Trending score 2.83

  4. 4
    RainBowLuoCS/Gamer

    Official Implementation of Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agents

    GitHub · 1,058 stars · 22 forks · +207 stars in 24 hours · Trending score 2.50

  5. 5
    zenstory-ai/video-recap-skills

    AI 视频解说 Agent 技能包:自动切镜、看画面写解说词、配音混音合成成片,可导出剪映/CapCut 草稿,无需 GPU | Agent skills for narrated video recaps & CapCut drafts

    GitHub · Python · 642 stars · 116 forks · +23 stars in 24 hours · Trending score 2.32

  6. 6
    lightseekorg/tokenspeed

    TokenSpeed is a speed-of-light LLM inference engine.

    GitHub · Python · 2,944 stars · 424 forks · +10 stars in 24 hours · Trending score 2.18

  7. 7
    StarTrail-org/PixelRAG

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

    GitHub · Python · 10,971 stars · 988 forks · +7 stars in 24 hours · Trending score 2.10

  8. 8
    NVIDIA-AI-Blueprints/video-search-and-summarization

    NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.

    GitHub · Python · 1,997 stars · 421 forks · +8 stars in 24 hours · Trending score 2.06

  9. 9
    qualcomm/GenieX

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

    GitHub · Go · 8,541 stars · 1,091 forks · +7 stars in 24 hours · Trending score 2.06

  10. 10
    modelscope/evalscope

    A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

    GitHub · Python · 3,716 stars · 586 forks · +5 stars in 24 hours · Trending score 2.01

  11. 11
    sgl-project/sglang

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

    GitHub · Python · 38,885 stars · 10,659 forks · −123 stars in 24 hours · Trending score 1.80

  12. 12
    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.

    GitHub · Python · 169,329 stars · 35,259 forks · −34 stars in 24 hours · Trending score 1.80

  13. 13
    video-db/skills

    Server-side video workflows for agents: ingest, understand, search, edit, stream.

    GitHub · 151 stars · 13 forks · +9 stars in 24 hours · Trending score 1.75

  14. 14
    NVIDIA-NeMo/Automodel

    🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

    GitHub · Python · 1,096 stars · 391 forks · +5 stars in 24 hours · Trending score 1.71

  15. 15
    Tencent/AngelSlim

    Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

    GitHub · Python · 1,808 stars · 200 forks · +4 stars in 24 hours · Trending score 1.51

  16. 16
    OmniJev/OneJev

    🚀🚀 A multimodal System One decision model that gives calibrated answers to typed questions about screens, photos, video and text in one forward pass.

    GitHub · Python · 274 stars · 28 forks · 0 stars in 24 hours · Trending score 1.27

  17. 17
    NVIDIA/context-aware-rag

    Context-Aware RAG library for Knowledge Graph ingestion and retrieval functions.

    GitHub · Python · 94 stars · 31 forks · +4 stars in 24 hours · Trending score 1.24

  18. 18
    EvolvingLMMs-Lab/lmms-eval

    One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

    GitHub · Python · 4,497 stars · 699 forks · 0 stars in 24 hours · Trending score 0.81

  19. 19
    dongxinsuperman/ai-phone

    iOS / Android / HarmonyOS 三端真机 + 三端虚拟机 AI 自动化中台 · 自然语言驱动纯视觉执行,开箱即用的设备调度、多设备并发与报告回传

    GitHub · Python · 135 stars · 26 forks · 0 stars in 24 hours · Trending score 0.80

  20. 20
    worldbench/awesome-vla-for-ad

    🌐 Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future

    GitHub · HTML · 527 stars · 60 forks · 0 stars in 24 hours · Trending score 0.67

  21. 21
    l8cv/BusterX

    [NeurIPS '26] BusterX & [EACL '27 Findings] BusterX++

    GitHub · Python · 54 stars · 2 forks · +1 stars in 24 hours · Trending score 0.64

  22. 22
    EnragedAntelope/EA_LMStudio

    ComfyUI node for local LLMs and vision models via LM Studio: prompt enhancing, image captioning, reasoning extraction, structured JSON output and VRAM management.

    GitHub · Python · 26 stars · 9 forks · +1 stars in 24 hours · Trending score 0.61

  23. 23
    hekmon/comfyui-openai-api

    Call LLMs and VLMs from ComfyUI with any OpenAI compatible chat completions API: local servers (llama.cpp, vLLM, SGLang, Ollama, LM Studio, tabbyAPI, Unsloth Studio…) or cloud providers. Text and image inputs, multi-turn history with memory loops, and model unloading for local servers.

    GitHub · Python · 57 stars · 18 forks · +2 stars in 24 hours · Trending score 0.59

  24. 24
    huggingface/optimum-intel

    🤗 Optimum Intel: Accelerate inference with Intel optimization tools

    GitHub · Jupyter Notebook · 630 stars · 300 forks · 0 stars in 24 hours · Trending score 0.58