Havuz

CSS Animations on steroids.

一套功能完整、轻量稳定的 ComfyUI 实用节点集。初衷是为了平替一些断更插件的功能，会持续更新一些新开发的节点插件。有好的创意可以发Issues，我会力所能及想办法做出来。全中文界面，原生控件，不依赖第三方库。

Stateless LLM runtime that dynamically routes, loads, executes, and unloads models per request with bounded VRAM caching and intelligent mod

Turn any Shopify catalog into product videos with the Runway API. One script, gen4.5 image-to-video.

An agentic LLM-powered knowledge assistant that enhances RAG capabilities through automated entity extraction, structured data analysis, and

AI 漫剧/短剧连载创作引擎（Agent Skill）| 一句话到剧本+分镜+配音+AI提示词的工业化流水线 | 七个记忆文件+22项跨文件一致性检查，解决长线连载人设崩坏与伏笔丢失 | Agent-agnostic (Claude Code / Codex / Copilot

A comprehensive hands-on, AI-first Python curriculum with 80+ interactive Jupyter notebooks for AI Engineers from core basics to LLMs, RAG,

AI-assisted travel planning with Gemini itineraries, Firebase persistence, and expense tracking.

An open library of reusable AI skills for procurement, sourcing, contracting and supplier management.

Image → ASCII art by direct optimization. Any monospace font, optional color.

Improved ReferenceLatent for ComfyUI — per-image strength, timestep gating, MediaPipe auto-masks, 1-4 image inputs. Works with Flux, Klein,

Multi-agent workflow orchestrator with MCP tool servers: planner/executor agents, tool-use loop, MCP client/server, tracing and durable runs

End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking cur

A ComfyUI diffusers implementation of Krea2 for the highest possible quality and most options

One-click tidy-by-role for ComfyUI workflows. Loaders / encoders / samplers / decoders / outputs each get their own column or row, with opti

Seedance 2.0 ComfyUI: custom nodes and workflows for ByteDance video generation via MuAPI — text-to-video, image-to-video, Omni Reference, c

Structured project workflows for Claude Code. Published v1.5.1: 54 skill manuals / 8 departments. Development source: 64 / 9, with peer CEO,

Production-ready Next.js AI SaaS boilerplate — Google OAuth, Stripe credit billing, Prisma, MuAPI AI engine, and webhook-backed async genera

Use Kimodo (and any MMCP motion model) in Blender — text-to-motion, text-to-pose, and constraint-aware generation onto your armature.

Codex / WorkBuddy 短剧带货 Skill：salpx 生成分镜首帧，salpx Wan 3.0 直出 2–30 秒视频（多图/视频/音频参考、原生音轨、口型同步），支持美国市场本地化与剧本保真。

A complete, hands-on journey from Python fundamentals to AI Engineering. Explore Data Analytics, Data Science, Machine Learning, Deep Learni

Curated Claude and Codex skill collection for local AI workflows, automation, research, and product-building.

Curated catalog of open, specialized AI agents for real business work — organized as broad umbrella categories (video, image, voice, SEO, so

HK NPU STUDIO — Local AI for Snapdragon® PCs. NPU-accelerated image generation for Windows 11 ARM64. Featuring Phoenix Boost.

Research Math Agents, Official code release for our paper RMA

Generative Models for Real-World Sensor Time Series

Building an Image-to-Video (I2V) Model from Scratch

Text-to-motion authoring for Unreal Engine 5.8, powered by Kimodo

A creative AI platform for discovering, sharing and exploring stunning AI-generated visuals and prompts

An Always-On Autonomous AI Software Engineering Team built with LangGraph, FastAPI, and Next.js that operates natively within your GitHub re

Generate broll for a video using AI

SDK for building on-device AI applications on Arm with reusable building blocks across inference runtimes.

FastAPI gateway for detecting and sanitizing PII before it reaches downstream systems. Built with LangGraph, Redis, and PostgreSQL.

AI 漫剧/短剧端到端制作 Claude Code Skills 包(Dreamina + edge-tts + ffmpeg)

Open-source AI character creator & roleplay chat studio — production-ready Next.js SaaS that generates custom AI character portraits and ena

Open-source Veo video generator — production-ready Next.js SaaS for text-to-video, image-to-video, and multi-image editing powered by Google

Runtime economic governance for AI agents. Circuit Breaker adds risk-managed execution, cost ceilings, and kill switches to autonomous AI wo

Official LFM-LLIE implementation—first-place winner of the NTIRE 2026 Low-Light Image Enhancement Challenge non-reference track.

Multi-model AI agent runtime. Define agents in YAML, route each role to a model, orchestrate with 7 patterns (ReAct, Plan & Execute, Fan-Out

Your all-in-one funscript editor, generator, and player. Free tracking algorithms. A Pro Pass unlocks the next level AI generation right on

Production-ready AI SaaS starter kit: a Next.js 16 + FastAPI monorepo with Supabase auth, Stripe billing, text-to-image AI generation (NVIDI

kiro-flock applies amorphous computing to generative AI: configurable clusters of Kiro agents on EC2 with amorphous, mesh, and swarm algorit

A tiny C runtime for durable AI agents: local-first, event-driven, restart-safe, and fully inspectable.

Local-first AI filmmaking workstation — Flutter Desktop with a node-based canvas wiring multiple AI image/video providers. macOS + Windows.

Open-source AI prompt engineering workspace — production-ready Next.js SaaS with conversational refinement, multi-engine targeting (ChatGPT,

OpenAI-compatible Go gateway for Vertex AI Gemini with explicit model routing, live catalog refresh, and Cloud Run setup.

A complete, structured end-to-end roadmap to become a versatile Generalist AI Engineer from Python/math foundations through ML/DL, CV, NLP,

Build and train a mini Kimi K3 from scratch — a pure-PyTorch playground from a custom 88M model to 2T-scale LLM profiles.

[NeurIPS 2026 E&D]WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors

Local-first novel-to-comic generator — free, no GPU, pluggable providers.