DEDUPEDVoice Studio
VoiceStudio is an open-source, local desktop app and API for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation.
4 use cases: Dub a video into timed speech locally; Turn a manuscript into an audiobook in batches; Dictate and transcribe speech without the cloud · GitHub
Anatomy
Anatomy is an agent skill that turns a technical idea into an interactive isometric figure built from physical parts, output as HTML, SVG, WebGL or 3D.
4 use cases: Explain a technical concept as an interactive HTML page; Create a standalone SVG illustration for a landing page; Build a figure with a WebGL fire or water effect · GitHub
Comfy UI
ComfyUI is an open-source node graph GUI, API, and backend for running diffusion models locally or in the cloud to generate images, video, audio, and 3D.
4 use cases: Generate images from ready-made template workflows; Run image and video generation fully offline; Turn a complex workflow into a simple app or API · GitHub
Hyperframes
HyperFrames is an open-source framework that turns HTML, CSS, media, and seekable animations into deterministic MP4 videos, usable through a CLI or AI coding agent skills.
5 use cases: Make a product launch video from a website URL; Turn a GitHub pull request into an explainer video; Add captions to a talking-head video without touching footage · GitHub
Earshot
earshot is an open source, CPU-only toolkit that gives coding agents the ability to describe, judge, search and generate sound through a CLI, a Python API and an MCP server.
4 use cases: Pick the best sound file from a set of downloads; Find the exact moment of a sound in a long recording; Check a launch film's sound and sync with an agent · GitHub
Fish Audio Hermes
A plugin for the Hermes Agent that gives it Fish Audio speech: text-to-speech, speech-to-text, a voice library, voice cloning and voice design.
5 use cases: Give your Hermes agent a spoken voice; Transcribe a recording with speakers and subtitles; Find a narrator voice and save it under a short name · GitHub
Product Launch Motion
A Claude Code skill that turns a website URL into a 30-second, 60 fps launch video with music, synced sound effects and motion blur, rendered locally from HTML.
3 use cases: Turn a website URL into a launch video; Add a WebGL glass pass to a launch film; Brief a new product film from the review-note prompts · GitHub
Manimgx
ManimGX is an animation engine that renders Manim CE-style 2D and 3D Python scenes to MP4 video or to a web page, using a Rust and wgpu core.
4 use cases: Render a 3D Python scene to a 1080p60 MP4; Have an AI agent build and open a 3D animation; Make a narrated explainer video synced to speech · GitHub
Machine Skill
Machine Skill is an open source Claude Code skill that builds a photoreal, physics based, interactive 3D simulation of a described machine as one HTML file, and can record a short film of it.
4 use cases: Build a cut-open pump page for plant operator training; Record a 28 second film of a machine for social feeds; Make a slowed mechanism to teach how it works · GitHub
Anidoodle
anidoodle is a TypeScript toolkit that lets a person or AI agent write illustrations, drawing timelapses, films, explainers and interactive web art as code, in 32 styles.
5 use cases: Cut a launch film for your product from a template; Make a set of brand illustrations for your website; Add an interactive mascot to a web page · GitHub
Blender AI MCP Addon
mcp-for-blender-pro is a Blender add-on that gives an AI assistant a chat workspace, scene tools and a built-in MCP server so it can inspect and edit a Blender scene.
5 use cases: Explain a Blender scene before changing anything; Build a product display scene from a short brief; Run a manager, worker and reviewer team on a scene task · GitHub
MCP for Blender Pro
mcp-for-blender-pro is a Python add-on for Blender that adds an AI chat assistant, a visual Studio workspace and a built-in MCP server so AI models can inspect and edit a Blender scene.
5 use cases: Inspect a Blender scene before the AI changes it; Build a product-display scene from a text brief; Find an asset and import it only after approval · GitHub
Beat Design
BeatDesign is an open-source, local-first workspace for AI image and video creation, with an infinite Canvas, a browser-based video Editor, and MCP tools that let coding agents work in the same project.
3 use cases: Edit local clips into an MP4 without an API key; Let an MCP agent edit the same timeline you see; Generate and branch images and video on a Canvas · GitHub
Motion Video Skill
An agent skill that guides an AI agent through producing beat-synced 1920×1080 motion-graphic videos with HyperFrames, a voice-over, karaoke captions, sound effects and generated music.
4 use cases: Make a beat-synced launch video from a script; Make a second style edition of a release video; Scaffold a motion video project by hand from templates · GitHub
Beyondwords
Beyondwords is a goal-driven AI assistant skill for planning, producing, publishing and advertising books on Amazon KDP, with support for Lulu and client book-production work.
4 use cases: Plan a first KDP book from an income goal; Produce ebook and print files for a KDP title; Run a bounded Sponsored Products ad test · GitHub
Index Translate
Index-Translate is a family of multilingual, multimodal translation models built on Qwen3.5, with a free OpenAI-compatible API and a command-line script.
4 use cases: Translate a screenshot or photo without OCR; Translate a text string from the command line; Use the API inside a browser translation extension · GitHub
Open Montage
OpenMontage is an open-source system that lets an AI coding assistant plan, generate, edit, and render videos from plain-language requests through 12 production pipelines.
5 use cases: Build a real-footage documentary montage for free; Turn a reference Short into a grounded production plan; Make an animated explainer with no paid API keys · GitHub
Comfy UI H3 Face Refine
A ComfyUI custom node set that tracks small faces in MiniMax H3 video, crops to each face, refines it with H3, and composites it back into the clip.
3 use cases: Refine small faces in a MiniMax H3 video; Pick the right face in a multi-person video; Check the face crop before a full H3 render · GitHub
Draw Your Font
A free, open source Node CLI and Claude Code skill that turns a photo of handwritten letters into an installable font (TTF, WOFF, WOFF2) and CSS.
4 use cases: Turn a handwriting photo into a font with Claude Code; Build a font from a photo with the CLI, no AI; Print a template to get a cleaner handwriting font · GitHub
Scumble
Scumble is a free, open-source Windows desktop image editor that uses AI models to inpaint, edit, upscale and generate, with each result returned as its own layer.
4 use cases: Replace part of a photo with an AI layer that matches; Generate a new picture from boxes and reference images; Let Claude Code edit pictures in Scumble through MCP · GitHub
Asamana
Asamana is an open-source Python and React engine that generates a themed world of AI characters that act on their own and produce a story without a script.
4 use cases: Replay a finished story without any API keys; Generate and run a new themed AI story; Audit a finished world's narrative quality · GitHub
Reelmimic
ReelMimic is a local tool that breaks down a reference video's style and uses an AI crew (Claude Code or Codex) to plan, build and review a new video in that style.
3 use cases: Make a new video in the style of one you love; Build a narrated comic with Taiwanese Mandarin voice; Post a finished video to social accounts safely · GitHub
Blender Skills
A set of 22 Blender 5.2 workflows packaged as Agent Skills that AI coding agents can load to model, texture, rig, animate, export and check 3D assets.
4 use cases: Make a game-ready Unreal crate with baked normals and LODs; Rig a character in Rigify and export a Unity walk cycle; Find z-fighting and floating parts, then export to Roblox · GitHub
Get Brolls
Get B-rolls is a skill that finds supporting video and image clips for a script, previews them, collects your choices on a storyboard for review, and delivers cut clips with their source records.
3 use cases: Find a literal NASA clip for a script line; Collect B-rolls for a Reel through Claude Code chat; Run a paced batch of social Reel B-rolls · GitHub
Brand Identity Skill
A Claude Code skill that designs brand identities as one system (logo, typography and colour palette from one brief), measures them, and delivers a brand guidelines kit.
4 use cases: Design a logo, type and palette for a new brand; Restyle your website's type and palette, keep the logo; Critique an existing brand identity with measured checks · GitHub
Showtime
showtime is a local video studio, delivered as an agent skill, command line and optional MCP server, where a coding agent plans a video and the user's own machine renders it.
4 use cases: Make a launch video from one sentence; Turn a Claude Code session into a narrated recap; Turn a failing Playwright test into a bug-report video · GitHub
Onetake
onetake is a Claude Agent Skill that makes continuous-take motion films (product launch films, teasers and feature demos) in which each beat visibly grows out of the one before.
4 use cases: Make a 15-second product launch film with one camera; Rebuild a feature demo from screenshots, no recording; Diagnose a motion video that reads like a slideshow · GitHub
Kokon
Kokon is a free, open source desktop app that edits and creates photos from text descriptions on your own GPU or Mac, powered by Qwen-Image 2.1, with an MCP server for AI agents.
4 use cases: Edit a photo by describing the change in plain words; Let an AI agent create and edit images on your machine; Remove or replace one object without touching the rest · GitHub
Framefields
Framefields is an Apache-2.0 TypeScript npm package that lets code and AI agents build compositing, motion graphics, and 3D video, then render it to MP4 directly on the GPU through WebGPU.
4 use cases: Render a title card to MP4 from TypeScript; Teach a coding agent to author Framefields videos; Build beat-synced motion graphics for a short video · GitHub
GPT Image Skill
GPT Image Skill is an installable skill that lets Codex, Claude Code, or Google Antigravity generate and edit GPT images through a ChatGPT subscription instead of the Images API.
5 use cases: Generate images from a text prompt in Codex; Revise an existing image without losing prior edits; Batch-create several distinct poster concepts at once · GitHub
Flow MCP
flow-mcp is a free, locally run program that drives Google Flow in a dedicated Chrome window so Claude, Codex or a local control panel can make AI images, video and narration using Flow credits instead of the pay-per-use video API.
4 use cases: Make a short AI film from one character; Batch-render scene stills at zero credit cost; Archive a Flow project's media locally at no cost · GitHub
Mortiflix OSS
Mortiflix is a self-hosted motion design studio where Claude builds videos stage by stage and you approve each stage.
5 use cases: Make a narrated explainer video, approving each stage; Run the video studio from inside Claude Code; Make a vertical social short that works without sound · GitHub
Watermarks Remover
A privacy-first Python service and agent skill that strips AI provenance marks from text and files you own.
4 use cases: Flag AI provenance marks in files Claude Code writes; Clean AI marks from manuscripts and web copy; Strip AI marks from files inside a Codex project · GitHub
Khan Explainer
A Claude Code skill that turns a written description into a Khan Academy style explainer video, with a pen drawing on a board while a voice explains, rendered locally to MP4.
4 use cases: Make a Khan-style explainer video from one sentence; Draw arrows and steps over screenshots for a product tutorial; Cut a YouTube video or podcast into vertical shorts · GitHub
DSH Agent RP
DSH Agent RP is a TypeScript roleplay runtime for DSH that runs characters as top-level agents and imports SillyTavern character cards, World Info, presets, and chat logs.
4 use cases: Chat with an imported character card in DSH; Move a SillyTavern JSONL chat into Agent RP; Write a serial story with the story engine · GitHub
Blender AI Addon
A Blender add-on that turns the 3D viewport into a chat with an OpenCode AI agent, which writes bpy Python code that the add-on runs in the scene.
4 use cases: Build a 3D object in Blender from a text prompt; Create a 3D model from a reference picture; Let the agent repair a failing generated script · GitHub
Claude Motion Design
A Claude Code skill that makes motion design videos entirely in code using HTML, Playwright and ffmpeg, with no After Effects or Remotion license.
3 use cases: Make a motion design video from a brief in Claude Code; Run the Howseen example film locally and re-render it; Remake a launch video frame by frame for your brand · GitHub
Remiqora
Remiqora is a free, open-source local music studio that runs ACE-Step 1.5, YuE2-3B and Stable Audio 3 on your own GPU, with a multitrack DAW, an AI arranger, stem separation, MIDI transcription and LoRA training.
6 use cases: Turn one phrase into a finished song track; Build a full arrangement part by part with the AI arranger; Split a track into stems and remix them in the DAW · GitHub
Pixel Path
A Claude Code skill that turns two places into a pixel-art, first-person fly-through of the real road, built from OpenStreetMap and elevation data.
4 use cases: Make a pixel-art fly-through of a real road trip; Build a driving or racing level from a real road; Learn an OpenStreetMap bake pipeline and pseudo-3D renderer · GitHub
Sonic Match MCP
Sonicmatch is a Python MCP server that watches a video, then returns license-labeled background music matches, a 12 to 20 second hook window, and an ffmpeg ducking spec for agents and editors.
4 use cases: Find license-labeled BGM and a ducking spec for a Reel; Pick one shared playlist for a batch of clips; Keep background music on brand with a saved kit · GitHub
Screenwriting Skills
A set of 26 agent skills for screenwriting, television writing and dramaturgy that Claude Code and OpenAI Codex can load and use.
4 use cases: Break a multi-episode series into acts and act outs; Rewrite on-the-nose dialogue in a scene; Turn a long novel into a series episode outline · GitHub
Skills
A set of agent skills, /awwwards and /jury, that build award-style websites from a one-line brief and score existing sites the way an Awwwards jury would.
4 use cases: Build a distinctive portfolio site from one line; Score a live website like an Awwwards jury; Compare your site against a competitor's · GitHub
Logo Design Skill
A logo-design skill, a folder of Markdown instructions and dependency-free Python tools that lets Claude, Gemini CLI, Codex CLI and other agents work through a logo brief to production-ready SVG files.
3 use cases: Design logo concepts for a new brand with an agent; Audit an SVG logo against design principles; Export a favicon, app icon and web manifest set · GitHub
Ffmpeg Skill
ffmpeg-skill is a local video editing toolkit for coding agents, with 42 FFmpeg-based tools, a machine-readable contract and an MCP server.
4 use cases: Cut an interview into a 60-second Reels clip; Turn a talking-head video into a captioned TikTok; Export one edit to nine social platforms at once · GitHub
Audio Studio MCP
Audio Studio MCP is a local MCP server that generates background music, instrument loops and sound effects with Stable Audio 3, then loops, normalizes and exports them, with no cloud service or API key.
4 use cases: Generate a seamless BGM loop for a game scene; Create a sound effect and export it for Godot; Extend or restyle an existing track with edit_audio · GitHub
Reimagine It
reimagine-it is a JavaScript CLI that redesigns an existing HTML page into a standalone HTML file, using the page's own headings, facts, links, dates, numbers, and colors.
4 use cases: Redesign an existing HTML page in one command; Show a client several ranked redesign options; Pin an approved redesign with a seed and report · GitHub
Jasna
Jasna is a free, GPU-based tool that finds and restores mosaics in videos and still images, with a desktop app and a command line.
4 use cases: Restore mosaics in a video with the Jasna app; Batch restore a folder of videos from the command line; Restore a single still image from the command line · GitHub
Yovoice
yovoice is an open-source, local-first studio for macOS and Windows that generates speech, cloned voices, songs with lyrics, and multi-track MIDI scores on your own machine.
5 use cases: Turn a text file into narration with an AI agent; Dub a script or subtitle file line by line; Generate a sung track from your own lyrics offline · GitHub
Cinetic
cinetic is an agent skill that makes a coding agent plan and render short launch films, loops and logo stings from code.
4 use cases: Make a 25-second launch teaser with sound; Create a 12-second vertical video for Reels and TikTok; Build a seamless 10-second muted loop for a landing page · GitHub
Blender AI MCP Addon
An AI assistant add-on for Blender that inspects your scene, builds and edits objects, and runs multi-step workflows through a chat workspace and a built-in MCP server.
5 use cases: Build a product-display scene from a text brief; Get a scene structure review before any edits; Split a large Blender task across an agent team · GitHub
XXG Portrait Rebuild Light
xxg-portrait-rebuild-light is a Python image-edit skill that relights existing portrait photos and repairs skin texture while keeping the person's identity, pose, and framing.
4 use cases: Relight a flat or weak backlit portrait; Restore natural skin texture in a smoothed portrait; Give a portrait a film or camera-device look · GitHub
HBG Classical Poem Silk Video
A Codex and Claude Code agent skill that turns a Chinese classical poem into a vertical Chinese-painting video, using generated stills, Docker image-to-video, brush-calligraphy captions, kept ambient audio, optional BGM, and final MP4 checks.
3 use cases: Turn a four-line poem into a vertical Chinese-art video; Check an existing poem video before you publish it; Repair weak image-to-video clips in a poem project · GitHub
AI Iso Skill
A Claude skill that turns a named object into one interactive isometric HTML figure, drawn in plain SVG with parts that respond when pressed.
3 use cases: Make a pressable isometric device figure in Claude.ai; Install the skill as a Claude Code plugin and draw figures; Learn how the skill builds isometric SVG from SKILL.md · GitHub
Sepia
sepia is a portable Agent Skill that de-AI-fies writing, repairing narrative structure in fiction and applying venue-matched rules to professional documents.
5 use cases: Repair a story draft's narrative structure in Claude Code; Check release notes and PR replies against venue rules; Draft a blameless postmortem with the Codex plugin · GitHub
Scroll Craft
scroll-craft is an agent skill that gives Codex, Claude Code, and other coding agents a design workflow, engine, and verification tools for building premium, scroll-driven websites.
4 use cases: Build a scroll-driven site from one Claude Code prompt; Turn your own footage into a scrubbing scroll page in Codex; Generate scroll-page imagery and video with a KIE key · GitHub
DeepSeek Whalechan
A Python repo with a Whale-chan character spec, visual asset library, and two agent skills for generating consistent character illustrations and multi-panel comedy comics.
3 use cases: Generate on-model Whale-chan illustrations for a poster; Turn an error log or chat into a Whale-chan comedy comic; Choose a chibi form for a high-density sticker set · GitHub
Helix World
HelixWorld is a Python research repo for a real-time interactive audio-visual world model that generates video and camera-aligned spatial sound from a starting image, a prompt, and movement or camera actions.
3 use cases: Render a first-person walkthrough MP4 from one image; Score whether generated sound follows camera motion; Walk through a Helix World scene in the browser · GitHub
Cozy Clay
CozyClay is an open source browser-based previs tool for blocking 3D scenes, posing characters, and planning camera moves before sending the shots to an AI video model.
4 use cases: Block a scene in 3D before paying for AI video; Direct the studio from Claude Code or Cursor; Let a coding agent drive a running studio from the terminal · GitHub
Humanizer Stack
A two-pass set of Claude Code Skills and Python scanners that removes AI writing tells from outward-facing text, first at the word level and then at the structural level.
4 use cases: Strip AI tells from a blog post before publishing; Block AI-tell copy from merging with a strict scan; Run the structural pass on a long draft or story · GitHub
Any Image
AnyImage is a Blender toolkit that turns images into planes, cutouts, and image-edited assets with materials, contours, and depth.
4 use cases: Paste a clipboard image straight into a Blender scene; Turn a reference image into a flat or depth plane; Cut out a subject and build a Surface, Balloon, or Depth Shape · GitHub
Openfilm
OpenFilm is an open source tool that lets a coding agent write films as web pages, and lets a person edit the result in a local browser editor called Studio.
4 use cases: Make a short launch video with a coding agent; Edit an agent-made film by hand in Studio; Hand a film to Final Cut Pro, Premiere Pro or DaVinci Resolve · GitHub
Openspline
OpenSpline is a Python and Node SDK that turns a portrait and generated audio into a synchronized talking avatar video, on OpenSpline Cloud or a self-hosted NVIDIA GPU.
4 use cases: Add a live talking face to a Python voice agent; Run a local avatar demo on your own NVIDIA GPU; Put a face on an OpenAI Realtime agent · GitHub
Human Review
A local visual review tool that lets you edit HTML and Markdown files and localhost pages in your browser, leave comments, and send all feedback to your AI coding agent in one batch.
3 use cases: Edit an AI-written Markdown plan and send feedback in one batch; Mark up a localhost page and send fixes back to the app source; Cut extra copy and rewrite CTAs across several pages · GitHub
Fable51 Worlds
A repo of procedurally generated 3D worlds built with Three.js, each walkable in a browser, with the generating code, verification scripts and QA reports included.
3 use cases: Walk a real San Francisco plaza in a browser; Change one building detail as a reviewable code diff; Check a generated world against reference photos · GitHub
Remocn Studio
Remocn Studio is a free, open source macOS and Linux app where your own coding agent builds videos as editable Remotion projects that you own on disk.
4 use cases: Make a launch video from a plain-text brief; Fix text and timing by clicking the element on screen; Keep every new video on brand with saved components · GitHub
Cinematic Video Prompt Skill
A Claude Skill and cinematography cheat sheet that helps AI write precise prompts for text-to-video and text-to-image tools.
4 use cases: Write a precise Veo 3 video prompt in Claude Code; Get cinematic video prompts from any chat AI; Keep one character consistent across several clips · GitHub
Blender Plugin
A GPL-3.0-or-later Blender extension that brings Scenario AI image, video, 3D, PBR material, audio and 360 environment generation into the Blender viewport, and exposes a local MCP server so agents can work on the open scene.
5 use cases: Generate a PBR material set and apply it to a mesh; Let a coding agent read and edit the open Blender scene; Turn a written scene description into a greybox layout · GitHub
Skills
A set of Agent Skills that teach AI coding agents to create images, video, audio, textures, and 3D assets through the Scenario MCP server, plus expert skills that drive DCC and game engine software.
5 use cases: Generate a matching set of game sprites and icons; Make seamless textures and 360 skyboxes for an engine; Shoot product packshots and scenes from a real photo · GitHub
Riso Windowseat
A GitHub repo of procedural risograph films and prints, each a single HTML file, plus Claude Code skills, craft docs and a render harness for making more.
4 use cases: Make a riso film from a one-line prompt; Export a riso poster as a 2160 x 2160 PNG; Fix a loud moment or score an existing film · GitHub
Shaders
Shaders is an MIT-licensed TypeScript library of over 200 WebGPU visual effects that you use as components in React, Vue, Svelte, Solid, or plain JavaScript.
5 use cases: Add an animated WebGPU background to a web page; Design a shader visually and export it as code; Keep designed Shaders in sync with your codebase · GitHub
Mesh Avatar Studio
Mesh Avatar Studio is a TypeScript project that turns one illustration into an animated 2D mesh avatar, with a coding agent preparing it and a local editor for fine-tuning.
5 use cases: Turn your illustration into an animated 2D avatar; Stream your avatar in OBS with webcam tracking; Try an avatar in the browser without installing anything · GitHub
Frametell
Frametell is an open source TypeScript tool that turns an idea or source material into a narrated explainer video, with an AI director agent drafting a storyboard you approve before rendering.
3 use cases: Make an explainer video from one sentence; Turn your notes or PDF into an explainer video; Have an agent render an explainer from a command · GitHub
Pocket Men with You
PocketMen with You is a local tool that turns two or more photos into an animated Codex companion pet, using open-weight image editing when the hardware allows it.
3 use cases: Install a Codex pet from two or more photos; Build a high-fidelity pet with the Qwen identity backend; Create a Codex pet with no OpenAI API key · GitHub
Mixamo LLM Mocap
A Python pipeline that turns a locked-camera video, filmed or AI-generated, into an FK animation on any Mixamo character, with scripted steps that an AI agent can run end to end.
4 use cases: Turn a locked-camera video into a Mixamo animation; Check a retargeted clip against its source video; Build a two-character fight scene from one video · GitHub
Hyperframes Motion Reel Skill
A Claude Code skill that turns a short theme into a beat-synced HyperFrames motion graphics video and renders it to MP4.
3 use cases: Render a 15-second beat-synced reel from one line; Make a vertical 9:16 product teaser for social; Build a character intro reel from your own assets · GitHub
Motionmaxxing
An agent skill that turns a brand website into a motion graphics film, with measured timing and scripted checks on the render.
3 use cases: Make a launch film from a brand website; Check an AI motion video against the mog gates; Build a typography-only brand sting · GitHub
AuK
AuK is an open-source 1.5B speech model that generates and edits speech from natural-language instructions.
5 use cases: Generate speech in a reference speaker's voice; Create speech from a voice description alone; Replace or remove words in an existing recording · GitHub
Rembrandt
Rembrandt is a free, open-source photo editor for macOS, Windows and Linux that develops RAW files, manages a photo library and runs AI features on your own computer.
5 use cases: Self-host a photo editor for your home network; Edit RAW photos in a free desktop app; Move a Lightroom Classic catalog into Rembrandt · GitHub
Saas Motion Kit
A kit of creative rules, 101 visual themes, a 24-transition atlas and a variety audit that helps you plan and build promo and motion videos for software products with HyperFrames and Claude Code.
4 use cases: Catch repeated effects in a promo storyboard; Pick a visual theme for a tone and audience; Break a reference film into shots and rhythm notes · GitHub
Open Edit
Open Edit is an open-source command-line tool that lets people and AI agents create and edit videos, including subtitles, motion graphics, slides, and renders, powered by VEED.
5 use cases: Caption a video locally with WhisperX at no cost; Send a finished edit to VEED's editor as a project; Render an HTML motion graphic to a frame-exact video · GitHub
3dviz Pro Max
A standalone agent skill, for Claude Code and Codex, that helps an agent turn a creative idea into a Three.js or Blender 3D scene and check the rendered frames.
4 use cases: Build an explorable 3D scene from a one-line idea; Make an interactive product assembly for design review; Create an interactive lesson on eigenvectors or Bloch spheres · GitHub
Explainroo
explainroo is a free, open source tool that turns a script and JavaScript scene file into a narrated explainer video or product demo MP4, with the voice, timing and rendering running on your computer.
4 use cases: Make a narrated explainer video from one topic; Build a product demo that clicks through your app; Render one video in wide and tall sizes at once · GitHub
Anything2 Explainer
An open-source Claude Code and Codex skill that turns a topic or document into a narrated, black-canvas motion-graphics explainer video built in code with Remotion.
4 use cases: Turn a topic into a narrated explainer video; Convert an article or document into a video; Build a video from your own narration audio · GitHub
Awesome Qwen Image
A curated list of checkpoints, quantizations, prompt rewriters, LoRAs, and tooling for Qwen-Image 2.1, Alibaba's 7B unified text-to-image and image-editing model.
5 use cases: Generate images with the official Qwen-Image-2.1 base model; Run Qwen-Image 2.1 in ComfyUI on an 8 to 12 GB GPU; Generate images in 8 steps with the official Turbo model · GitHub
Aseprite AI Artist
An MCP server and skill set that lets a coding agent draw, review, animate and export pixel art directly in an Aseprite window that is already open.
4 use cases: Draw a pixel sprite live in your open Aseprite; Animate a sprite and export a spritesheet for your engine; Get a blind critique of your pixel art before shipping · GitHub
Printfilm
PRINTFILM is a self-hosted, MIT-licensed Python and React platform that turns a topic or script into AI short videos and AI short dramas (comics with video), using TokenFree models.
4 use cases: Run PRINTFILM locally with Docker in about 30 minutes; Turn a product topic into a finished short promo video; Produce an AI short-drama episode with consistent characters · GitHub
Awesome GPT Image 2 5 Prompts
A library of 150 GPT Image prompts, copied verbatim from the people who published them, credited to their authors and grouped by use case.
5 use cases: Turn a credited poster prompt into your own campaign visual; Generate a repeatable product shot series from the JSON data; Render ad creative with exact on-image copy · GitHub
DMAD
DMAD is a Python repo with 4-step LoRA students of the MiniMax-H3 33B model that generate 1344x768 video with stereo audio from text prompts, plus inference, ComfyUI, and training code.
4 use cases: Generate a 4-step audio-video clip from a text prompt; Make 5 s audio-video clips on an 8 GB consumer GPU; Render DMAD clips in ComfyUI with ready-made workflows · GitHub
Unbagrnd
unbagrnd is a free, open-source desktop app, with a self-hostable REST API, that removes image backgrounds using an AI model that runs on your own device.
4 use cases: Remove backgrounds from a whole folder of photos offline; Clean up hair edges and export a mask for design tools; Run the desktop app from source for development · GitHub
Other categories · All use cases · Hot repos
Questions
What is the best AI repo for Content in 2026?
Right now the top pick on Deduped is Voice Studio: VoiceStudio is an open-source, local desktop app and API for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation.
How are these Content repos ranked?
By how hot they are on GitHub (stars gained and mentions in the AI sources we track), then by how many practical use cases we found. The list is rebuilt every day.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them free