
Creates seeded, interactive generative art in p5.js starting from a written philosophy
- Free
- 196K GitHub stars
- Design and media

Creates seeded, interactive generative art in p5.js starting from a written philosophy

Builds, edits and checks PowerPoint decks with pptxgenjs, XML editing and rendered QA

Makes animated GIFs sized and optimized for Slack with PIL frames and a validator

Builds React and shadcn/ui artifacts and bundles them into one self-contained HTML file

Maps unmapped Figma components to matching code components using Code Connect

Writes project-specific Figma-to-code rules into CLAUDE.md, AGENTS.md or Cursor rules

Builds a Figma design system from code in gated phases: tokens, pages, then components

Rules and pitfalls for running Plugin API scripts in Figma files through use_figma

Choose the right SageMaker serving container and current image URI for a model

Generates and edits images through OpenRouter's Gemini 3 Pro Image model

Turns written text or summaries into a listenable MP3 using local neural speech

Lets your agent create and edit draw.io diagram files with valid mxGraph XML

Lets your agent generate draw.io diagrams as .drawio files and export them to PNG, SVG

Lets Codex generate or edit raster images like photos, sprites and cutouts

Guides an agent through designing, validating and deploying GCP infrastructure

Generates, extends and edits videos with Gemini Omni 1.2 Flash via the google-genai SDK

Checks a flashed NVIDIA Jetson BSP image statically and on the running target

Guides an agent through deploying and testing NVIDIA Nemotron Speech ASR, TTS and NMT

Diagnoses and optimizes OpenUSD stages for load time, memory and frame rate

Orchestrates Cosmos AnomalyGen defect image generation for PCBA, metal and glass

Orchestrates video data augmentation and auto-labeling runs on the OSMO platform

Guides fine-tuning of NVIDIA Cosmos3 reasoning models with Cosmos Framework or Cosmos-RL

Computes image embeddings from a parquet of file paths using CLIP, SigLIP or TAO

Generates synthetic object-detection defect images with COCO labels via AnomalyGenNext

Turns raw videos into chain-of-thought QA training data using VLM and LLM teacher models

Mines look-alike source images for VCN augmentation via DEFT embedding

Mines unique source images closest to target samples for object detection datasets

Runs an iterative RT-DETR retraining loop for binary industrial defect detection

Composes and deploys an NVIDIA VSS vision stack with captioning, detection, search

Calibrates multi-camera MP4 recordings through the AutoMagicCalib REST API
See every kind of AI for design and media: tools, agents, MCP servers and skills.Ranked: the best AI for design and media.