A curated collection of fun and creative examples generated with Nano Banana🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the community's development…

一个功能完整的视频自动化处理系统，支持从 YouTube 等平台下载视频，自动生成字幕、翻译内容、生成元数据，并定时上传到 Bilibili。

Animation engine for explanatory math videos

Allow LLMs to control a browser with Browserbase and Stagehand

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

Anthropic's Interactive Prompt Engineering Tutorial

The highest quality SaaS starter with Next.js, Supabase, Stripe, and shadcn/ui

Automate browser based workflows with AI

Public repository for Skills

SoulX-Podcast is an inference codebase by the Soul AI team for generating high-fidelity podcasts from text.

A powerful GUI app and Toolkit for Claude Code - Create custom agents, manage interactive Claude Code sessions, run secure background agents, and more.

Official repo for paper "Video-As-Prompt: Unified Semantic Control for Video Generation"

命令行投稿(B站)和视频下载工具，提供多种登录方式，支持多p。

A browser extension that helps users publish content to multiple social media platforms with one click.

练习英语，一次敲击，一点进步；Practice English, one strike, one step forward

Stagehand-GLM 是基于 stagehand-python 深度定制的AI浏览器自动化框架，专门适配了智谱AI的GLM文本和多模态大模型。它提供了渐进式的RPA操作策略，让开发者在智能便捷和成本效益之间找到最佳平衡点。

The best ChatGPT that $100 can buy.

Open-Source AI Presentation Generator and API (Gamma, Beautiful AI, Decktopus Alternative)

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

Chrome DevTools for coding agents

一款专注于Ai翻译的工具，一键自动翻译RPG SLG游戏，Epub TXT小说，Srt Vtt Lrc字幕，Word MD文档等等复杂长文本。

HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Qwen Image models through MPS

A powerful tool that translates ComfyUI workflows into executable Python code.

LLM agents built for control. Designed for real-world use. Deployed in minutes.