Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
HunyuanWorld-Mirror
Modelsimage to 3d model by tencent
tencent/HunyuanWorld-Mirror -
vibe-knowledge
SkillsVibe 知识大赏:一个知识点 → 一条有旁白、每句有出处的精品知识短片(Claude Code skill · 44 套风格 · 代码逐帧成片)
git clone https://github.com/andyhuo520/vibe-knowledge.git -
image to video model by WAS · minimax-h3
WAS/Minimax-h3_Singularity_v2_pruned -
MiniCPM-o-2_6
Modelsany to any model by openbmb · transformers
openbmb/MiniCPM-o-2_6 -
VideoJev-4B
Modelsfeature extraction model by ZhuYuhan · transformers
ZhuYuhan/VideoJev-4B -
Minimax-H3-R2VA-Veda-Preview
Modelstext to video model by Veda-Sparse · minimax-h3
Veda-Sparse/Minimax-H3-R2VA-Veda-Preview -
gemma-3n-E4B-it
Modelsimage text to text model by google · transformers
google/gemma-3n-E4B-it -
ai-creator-academy
Agents & frameworksFree, open-source curriculum for making money with generative AI image, video, and audio — for creators and agencies.
git clone https://github.com/Anil-matcha/ai-creator-academy.git -
VideoGLaMM
Agents & frameworks[CVPR 2025 🔥]A Large Multimodal Model for Pixel-Level Visual Grounding in Videos
git clone https://github.com/mbzuai-oryx/VideoGLaMM.git -
locally-uncensored
AI repositoriesThe all-in-one local AI studio for your desktop: chat, image and video generation and a coding agent in one free, open source app. Windows and Linux. No Docker, no terminal, no cloud required.
git clone https://github.com/PurpleDoubleD/locally-uncensored.git -
ai-film-skills
PromptsOpen Film Skills: 21 independent modules for story, directing, visual assets and AI-film production, with research galleries and playable 3D previs.
git clone https://github.com/62656456/ai-film-skills.git -
taishang-laojun
Prompts太上老君·AI炼丹炉:抖音/小红书短视频创作 Skill。不知道拍啥、不会写稿,丢给你的 AI:找对标拆爆款、选题、系列策划、口播稿、标题、复盘、去AI味。Claude Code / Codex 等 npx 一行安装,豆包等聊天智能体用 Bot 版。
git clone https://github.com/liuhaisi2026212-maker/taishang-laojun.git -
xperience-10m
Datasets & benchmarksHugging Face dataset by ropedia-ai
ropedia-ai/xperience-10m -
comfyui-h3-editor
SkillsA timeline video editor for MiniMax H3 inside ComfyUI: write shots, render them on your own GPU, cut picture and sound together, or let an agent make the video.
git clone https://github.com/igorls/comfyui-h3-editor.git -
Papermorph
SkillsAn AI skill that turns books into animated, narrated, interactive web experiences
git clone https://github.com/DozenTwelve/Papermorph.git -
superCMO-skills
SkillsOpen-source skills that empower any AI agent (Claude, Cursor, Hermes, etc.) to generate end-to-end marketing campaigns - UGC videos, ad videos, product photography and more.
git clone https://github.com/SupercmoHQ/superCMO-skills.git -
video to video model by slmonker · comfyui
slmonker/Open-H3-Regenerate-2K-IC-ComfyUI -
article2media
Skills把一篇文章或一条视频(抖音、B 站、YouTube,先转逐字稿)一键做成小红书图文、杂志长图、公众号排版和 AI 配音口播短视频的开源 Claude Code / Codex Skill。21 套主题,自动验收,零 npm 依赖。
git clone https://github.com/threerocks/article2media.git -
model by Momoking · comfyui
Momoking/Qwen3-VL-32B-Heretic-MiniMax-H3-NVFP4 -
MiniMax-H3-Director-Cut-Studio
PromptsPremiere-inspired PySide6 director studio for MiniMax H3 Ref2VA with AI shot planning, semantic media enrichment, timeline prompt reconciliation and shot-aware long-video rendering through ComfyUI.
git clone https://github.com/karuvanan/MiniMax-H3-Director-Cut-Studio.git -
mcp-video-analyzer
MCP serversMCP server that turns any video — YouTube, Instagram, TikTok, Loom, X, Vimeo, direct URLs, local files — into transcripts, key frames, OCR text, and metadata for AI agents.
git clone https://github.com/guimatheus92/mcp-video-analyzer.git -
Cosmos3-Nano
Modelsmodel by nvidia · cosmos
nvidia/Cosmos3-Nano -
LocalAI
AI repositoriesLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
git clone https://github.com/mudler/LocalAI.git -
tt-metal
AI repositories:metal: TT-NN operator library, and TT-Metalium low level kernel programming model.
git clone https://github.com/tenstorrent/tt-metal.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.