Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Vision-language models, document understanding and any-to-any architectures.
Signals: multimodal, vision-language-model, vlm, clip, multimodal-llm, visual-question-answering, document-understanding, image-captioning
339 results
Give Claude the ability to watch any video. /watch downloads, extracts frames, transcribes, hands it all to Claude.
面向 AI 创作的开源无限画布工作台，集成 AI 生图、参考图编辑、视频生成、Agent 智能助手、画布编排、对话创作、提示词库与素材管理等能力，支持可视化创作流程与多 Agent 协同工作。兼容 OpenAI 接口生态，支持 chatgpt2api、grok2api、flow2api、newapi 等渠道接入。
【影策】面向 AI 影视创作的开源无限画布工作台，集成多模态生成、分镜编排、素材管理与 Agent 工作流。
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
👾 AI-native Visual Analytics framework build for agents.
[ECCV 2026 Best Paper Award Candidate] LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
Visualize, query, and stream to train on multimodal robotics data.
面向 AI 影视、漫剧与多模态内容生产的 Agent 原生无限画布, 主推一键成片 agent，编排可控
SeaTunnel is a multimodal, high-performance, distributed, massive data integration tool.
One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
Cross-platform on-device AI toolkit
Claude support for Apple Foundation Models
Open Source project using LLMs to transcribe and translate subtitles (SRT, SSA/ASS, VTT)
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.
An extensible, state-of-the-art framework for columnar compression, and the fastest FOSS columnar file format. Formerly at @spiraldb, now an Incubation Stage project at LFAI&Data, part of the Linux Foundation.
👀 Train a 65M-parameter VLM from scratch in just 2h!
Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.
Build realtime multimodal AI agents with Node.js
Next-Gen AI Translation Tool Powered by LLM. Support Office documents, PDF, TXT, and more format with just one click.
Houdini Agent - DCC Asset Manager with AI capabilities
SciPilot Skills family - Publication-grade scientific figure copilot for Claude Code
Nurture your own AI assistant on your own computer. Local-first and MIT: memories, data and apps stay as plain files in your workspace. Chat summons the right GUI — wiki, spreadsheet, chart, form, 3D. Build small apps for an audience of one, no programming required.
Production ready toolkit to run AI locally
24,545 repositories in the index in total.
