video-generation

calesthio/OpenMontage

Turn Claude, Copilot or Cursor into a video production studio — OpenMontage adds 12 production pipelines, 100+ tools and 700+ agent skill files that teach coding assistants like Claude, Copilot or Cursor to plan, generate and edit video end-to-end. It even lets you paste a video you like as a starting reference, aimed at developers who want agentic video workflows without proprietary tools.

World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.

hypit-ai/hypit

Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and get your 100M views.

latent-spaces/brag

You built it. Now brag. Turn the project you just created into a short, shareable launch video with one command.

Vincentwei1021/video-shotcraft

Turn Claude Code or Codex into a cinematic product-video director — An AI agent skill that captures your real app screenshots and copy, then storyboards and animates a promo video with Remotion—no generative video model involved. It ships 152 tuned shot recipes, 209 motion previews, and a production-ready template, aimed at developers who want editable, on-brand code-driven videos.

AI video skill for Claude Code & Codex — cinematic, editable product promos with Remotion: 124 shot recipe cards, 150 motion previews, beat sync, sound design, Motion Workbench & JianYing (CapCut CN) export.

krillinai/OpenCreator

Rebranded KrillinAI becomes a Codex-powered creator workspace — OpenCreator, formerly KrillinAI, wraps Codex CLI with a local Runtime and visual workspace so creators can download, translate, dub, and edit video, images, and voice through reusable Agent Skills. It targets YouTuber, TikTok, and Instagram creators who want local, agent-driven production without rebuilding an agent loop themselves.

Formerly KrillinAI, VideoTranslation and Dubbing Tool. Open-source AI workspace for creators, powered by Codex. Video downloading, video translation, create videos, images, voice, avatars, and edits with Agents in one place. Suitable for your Social Media like YouTube, TikTok, Instagram, etc.

darkzOGx/youtube-automation-agent

A self-hosted AI agent that runs your YouTube channel, with your approval — This Node.js agent researches topics, writes scripts, generates narration, visuals and MP4s, then schedules uploads only after you approve them. It supports multiple text and video providers (Gemini, OpenAI, OpenRouter, DeepSeek) and learns from analytics for future videos, all running on your own machine with your own API keys.

🎬 Open-source, self-hosted AI agent that runs a YouTube channel end to end: researches topics, writes scripts, generates narration, visuals and video, optimizes SEO, and publishes after your approval, then learns from analytics. Works with Gemini, OpenAI, OpenRouter, DeepSeek and more.

PurpleDoubleD/locally-uncensored

A single desktop app for local chat, image, video, and coding AI — Locally Uncensored bundles chat, image/video generation and a coding agent into one free desktop app for Windows and Linux. It runs fully locally with no Docker, terminal or cloud, aiming at users who want private, uncensored AI without juggling separate tools or config files.

The 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.

xuanyustudio/LocalMiniDrama

Offline AI drama studio: script to finished video, no cloud — An Electron/Vue app that takes a story through script, characters, storyboard and video synthesis entirely offline, storing data in local SQLite. Connects to multiple AI providers (Tongyi, Volcano, Kling, Gemini) and adds a new in-episode assistant plus a canvas view for batch storyboard editing. Suited for creators wanting full control without subscriptions or cloud uploads.

🎬 seedance2接入 开源本地 AI 短剧 & 漫剧生成工具 —— 从故事到成片一站式完成，数据不出本机，短剧工作流管理平台，高灵活度，AI真人剧，AI漫剧本地搞定。 Open-source local AI short drama maker: story → storyboard → video, fully offline, your data stays yours. 纳米流水线

joeseesun/opus-video-prompts

Claude Opus 5.5 用代码生成视频：全网案例与可直接复制的提示词 | Copy-ready prompts & 54 cases of Opus 5.5 code-rendered videos

nvidia-cosmos/cosmos-transfer2.5

NVIDIA's World-Simulation Model Steps Aside for Cosmos 3 — Built on Cosmos-Predict2.5, this model generates world simulations from multiple spatial control inputs for physical AI research. The repo is now in limited maintenance, as NVIDIA directs development toward the unified Cosmos 3 platform, which merges reasoning, prediction, and transfer into one architecture.

Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control inputs.

vincentsch/explainroo

Explainer videos and product demos made by your AI agent. Free and open source: a local voice (Kokoro), word timing (Whisper) and a canvas renderer turn a script into a narrated MP4.

shadcn-labs/snapcn

Ready-made Remotion components for demo videos, installed via shadcn CLI — snapcn is a shadcn registry of Remotion components — text reveals, terminal sessions, device frames, AI chat streams, captions — installed with a single CLI command and owned as source in your repo. A browser-based editor can compose a full video and export an MP4 with nothing installed, useful for quick product demos.

A shadcn registry of Remotion components for product demo videos. Install a text reveal, device frame, terminal session, logo sting or a whole scene with a command.

sitor-ai/frametell

Frametell: turn your ideas and material into vivid explainer videos with an AI director agent. Local-first, any model.

VAST-AI-Research/EdenLive

Real-time generative rendering turns any reference video into game-ready visuals — EdenLive decouples interactive world state (run by engines or coding agents) from appearance, which it renders in real time guided by a first frame and text prompt. It hits 24+ FPS at 480P/720P on a single consumer GPU, with open 5B/14B weights, streaming inference code, and an EdenGolem skill that turns a prompt into a playable game prototype.

Real-time generative rendering for interactive worlds, from any visual reference.