A searchable library of ready-made prompts, presented as cards for tasks such as writing, office work, marketing, programming, and education. It supports keyword search, tags, sorting, and personal saved collections for use with ChatGPT, Claude, Gemini, Cursor, and similar tools.
A JavaScript library for creating animations with a consistent system for changing CSS properties, SVG, web-page elements, and JavaScript values over time. Optional adapters can handle Three.js and WebGL scenes.
A JavaScript animation framework with shared systems for timelines, easing, and timed value changes. It can animate CSS, SVG, Canvas, WebGL, framework state, and other JavaScript objects, with extensions for tasks such as scroll triggers, drag interactions, motion paths, and text animation.
A skill collection described as covering AI image-director abilities, along with information about what it is, how to install it, and how to use it. The available description does not specify individual capabilities.
A local desktop app that records a person's screen, window changes, visited pages, and optional voice description while they complete a task. It then uses GitHub Copilot CLI to turn the recording into an ordered description of the task and steps.
An organisation runtime for turning an AI assistant into a group of role-based workers. It creates an organisation structure, breaks work into dependent tasks that can run in parallel, tracks approvals and handoffs, and stores organisational memory.
An open-source job-application framework built for Claude Code that uses a personal profile to assess job matches, tailor CVs, write cover letters, and prepare interview responses. A CV is a document describing your work history and skills.
A command-line tool for reading, writing, and editing Word, Excel, and PowerPoint files without Microsoft Office installed. A command-line tool is controlled by typed commands or by software rather than by clicking through an app.
A local text-to-speech tool that turns ePub, PDF, plain-text, Markdown, or subtitle files into audio with synchronised subtitles. Text-to-speech means converting written words into spoken audio, and it runs on your computer without an API key.
A React 19 design system with accessible TypeScript components, customisable themes, dark mode, page templates, and command-line tools for AI agents. A design system is a reusable set of interface components and visual rules.
An open-source REST API for automating CapCut, a video-editing app. It can create drafts, add media, set effects, and save drafts so an AI agent or workflow can control those actions.
An infinite-canvas plugin that opens a tldraw drawing board inside Codex. It lets people and Codex sketch, annotate, generate images, and revise them together, with the canvas saved in the project folder.
An agent skill that creates single-file, landscape HTML presentations instead of .pptx files. HTML and CSS are plain text that an agent can read, edit, and check, and the result opens directly in a browser without a build step or server.
A set of rules for managing the production of AI-generated video as a film. It does not generate models, charge for services, download or upload media, or publish content; it focuses on organising how the production is made.
An open-source framework that turns HTML, CSS, and seekable animations into predictable MP4 videos. It is designed so coding agents such as Claude Code or Cursor can create videos from instructions.
An open-source framework that generates video from audio, matching speech with lip movements, head motion, body posture, and facial expressions. It is designed to keep the person recognisable while producing videos of unlimited length.
A command-line tool for MediaKit that covers both local FFmpeg editing and cloud-based AI media processing. FFmpeg is a widely used tool for converting and editing audio and video from the command line.
An open-source vector design tool built around AI-assisted work, with a Rust core, GPU rendering, and a React interface. It runs as a desktop application on macOS, Windows, and Linux, as well as on the web.
An open-source screen recorder that automatically follows the cursor with zooms and cursor animation, adds local offline captions, and exports MP4 or GIF files. It is intended for product demonstrations and walkthroughs.
A native macOS video editor built with Swift, with AI generation available directly in its timeline. It can also connect Claude, Codex, or Cursor through MCP, a way for software tools and AI agents to communicate with an application.
A local desktop canvas for keeping an AI creative project in one place. It brings reference material, prompts, scripts, storyboards, agent conversations, generated results, decisions, and lessons learned together as project files.
A local-first voice studio that combines voice cloning, text-to-speech, dictation, and agent voice output. It can clone a voice from a few seconds of audio, generate speech in 23 languages through seven engines, and run locally.
A text-to-speech system that turns written text into natural-sounding speech without first converting it into discrete text tokens. VoxCPM2 supports multiple languages and produces audio at up to 48 kHz.
A tool that extracts practical methods from books, long videos, podcasts, interviews, courses, and long articles, then turns them into reusable instructions for AI agents. It is designed to produce skills that can be combined and tested.
★not rated 2 todayA0 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: