LongCat Video
LongCat Video is an open 13.6B-parameter video model for text-to-video, image-to-video, and video continuation. The official release targets 720p, 30fps generation and longer coherent seque...
See why it fitsDescribe what you want to finish. We will route you to a useful tool, a ready prompt, a photo Look, or a complete workflow.
Hand-picked shortcuts for creating, learning, building, and staying safer online. No AI required.
A fresh starting point from every part of the hub. Pick the format that matches where you are stuck.
LongCat Video is an open 13.6B-parameter video model for text-to-video, image-to-video, and video continuation. The official release targets 720p, 30fps generation and longer coherent seque...
See why it fits
Photo LookPick the finish firstUse a crafted visual direction with your own photo.
6-step workflowCreate a faceless YouTube videoOne repeatable content pipelineRun the playbook A rotating shelf from the curated feed, with manually selected gems shown first.
Lingbot-map is an open-source streaming 3D reconstruction model from Robbyant. It combines geometric context, camera trajectory memory, and efficient...
Stable Diffusion 3.5 is an open, customizable image model family with Large, Large Turbo, and Medium variants. Medium is the practical starting point...
OpenManus is an open framework for building agents that plan tasks, use tools, browse, work with files, and run code. It is a useful starting point f...
Browser Use is an open-source framework and cloud service for agents that navigate and operate websites. It is useful for research and repetitive web...
FreeTTS combines text-to-speech, speech-to-text, vocal removal, voice enhancement, and browser audio editors in one workspace. Its current free plan...
IMGTrans translates text inside screenshots, photos, product images, and scanned pages while trying to keep the original layout intact. It is a pract...
Focused shelves from the same cached catalog feed. No extra homepage database reads.
Opinionated paths that explain what to use, in what order, and what the finished result should be.
Build / 2 stagesBuild faster with Gemini CLISet up Google's free terminal assistant, give it repository context, and use it for real coding work. A working terminal AI setup
Create / 6 stagesCreate a faceless YouTube videoMove from one channel idea to a script, voiceover, visuals, edit, thumbnail, and upload-ready video. One repeatable content pipelineGo straight to a focused shelf when you already know the category.