Havuz

Build & Auto-Optimize LLM Apps in 2026: The Ultimate AdalFlow Guide

Premiere-inspired PySide6 director studio for MiniMax H3 Ref2VA with AI shot planning, semantic media enrichment, timeline prompt reconcilia

AI image and video generation skill for Claude Code and other coding agents — Gemini, OpenAI and Kie AI behind one CLI and MCP server, with

Turn pets, selfies, characters, or anything into a full set of AI chat stickers.

Agent Skills for working UX designers. Challenge ideas, find blind spots, use the real design system, preserve evidence and decisions, and c

本地 ComfyUI 抽卡引擎，解决不会写提示词的问题。

Run the native 284B-A13B DeepSeek-V4-Flash-0731 LLM locally on one laptop CPU: pure C, 8 GB RAM minimum, no GPU, best TPOT 0.892 s/token, re

A native macOS lab for teaching tiny language models to think — build the architecture, train the weights, and watch a small LLM emerge from

Invisible, key-verifiable watermarks for AI/LLM-generated text — SynthID-Text-style, in Rust + WebAssembly (Node + browser). Live playground

Open-source visual ontology and constraint engine for inspectable reference-guided image generation. Try Virtual Try-On and Cosplay in the P

Refine and improve the quality of small faces in MiniMax H3 video. Per-frame face tracking, crop, refine with H3, stitch back.

An open-source, agent-guided creative-direction workflow for turning one visual reference into a connected brand system with Lovart Agent.

A tap-to-explore picture book where an AI draws every page in real time — type anything, click anything inside, and it draws a new page abou

4DAnyone, tek bir monocular videodan farklı kamera açılarında zamansal olarak tutarlı videolar üretip 4D Gaussian Splatting için girdi sağlar.

Neden yükseliyor · 48 günde 1.384 yıldız almış; README'de esnek kamera düzenleri, 4DAnyone-Turbo, GUI ve RTX 4090'da paylaşılan inference ölçümleri öne çıkarılıyor. Ancak son 28 günde 26 commit'in tek yazardan gelmesi, ilginin bağımsız geliştirici etkinliğiyle aynı şey olmadığını gösteriyor.

200+ AI, Gen AI, LLM, agentic AI, Forward Deployed Engineer (FDE), AI systems architect, applied AI, LLMOps and AI platform engineering inte

Local-first desktop agent that turns a prompt into a reviewed, playable browser game with Codex App Server.

Turn photos into source-faithful editorial artworks with an Agent Skill — adaptive layouts, controlled abstraction, and a Strict Fidelity co

AI visual director for turning personal photos into structured, editable visual narratives.

AI short-drama story architecture, Studio routing, model-aware shot timelines, continuity, validation, and resumable workflows for Codex and

Evolutionary multi-agent runtime that breeds, evaluates, and improves autonomous agents across reproducible epochs to converge on optimizati

Pure MLX MiniMax-H3 text-to-video-and-audio inference for Apple Silicon.

A full-screen terminal environment for writing fiction with language models.

🪐 HelixWorld: real-time interactive audio-visual world model.

Agent Skill for turning Chinese classical poems into vertical Chinese-art videos with ImageGen stills, Docker I2V, calligraphy captions, ret

ComfyUI nodes and tested workflows for MiniMax H3 still-image generation, reference editing, and Qwen detail refinement.

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

A featherweight spec-driven development template with a Memory Bank, for Claude Code, GitHub Copilot and JetBrains Junie.

Claude skill that turns a single request into a narrated mythic short film in a layered cut-paper diorama style — three-colour cardstock wor

🔥 On-Policy Self-Distillation in Diffusion Models

Open-source, model-agnostic AI company research for long-term investors. · 面向长期投资者的开源、模型无关 AI 公司研究系统。

🚀 One API gateway for GPT, Claude, Gemini, DeepSeek and more. OpenAI-compatible API for developers.

MIT-licensed TypeScript runtime for AI-native game characters and worlds, with durable state, reliable actions, memory, tools, and Unity, Go

Real-time AI creative preview plugin for Cinema 4D

Zero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime.

514 Krea 2 Turbo prompts with generated examples and ComfyUI wildcards

为中文公众号文章生成真实 3D 毛毡质感的封面、正文配图与精确插入指南的 Codex Skill。

AWS-native knowledge graph RAG framework unifying two graph-retrieval methodologies — Microsoft GraphRAG community summarization and LightRA

Tiny local text-to-24x24 pixel art model, trained on roughly 200K samples in 30 minutes on an RTX 5090.

Flatkey CLI, Flatkey hizmeti üzerinden image, video, audio ve text generation işlemlerini terminalden çalıştıran bir komut satırı aracıdır.

Neden yükseliyor · 73 günde 911 yıldız alması ve README'deki çoklu medya desteği ile agent odaklı kullanım iddiası dikkat çekiyor; ancak yükselişin nedenini doğrulayacak kullanım verisi yok. Son 28 günde 3 commit ve 2 farklı yazar, yıldız ilgisine kıyasla sınırlı aktivite gösteriyor.

Marketing Studio is a self-hostable AI video ad studio for e-commerce: UGC product ads, reference-ad remakes, AI drama ads, and ad skits, po

东方文化编辑海报 v2 Codex skill：Image 2 出图、中文标题精炼、真实文化物证、A/B/C 三联测试

A visual benchmark testing whether leading coding agents repeat the same design patterns across 100 neutral website briefs.

Model-neutral AI workspace for macOS with multi-provider models, extensible tools, and inspectable deliverables.

Codex içinde çalışan, kaynaklardan görsel ağırlıklı sunumlar üretip PPTX veya PDF olarak dışa aktaran bir AI slide studio.

Neden yükseliyor · 79 günde 919 yıldıza ulaşması erken dönemde dikkat çektiğini gösteriyor; Codex içinden çalışması, sürecin görünür olması ve hazır stil şablonları ilgi çekici bir ürün vaadi sunuyor. Ancak yükselişin nedenini doğrulayacak büyüme verisi yok; son 28 günde commit ve farklı yazar sayısı da sıfır.

Vox Director, bir konuyu script, collage görselleri, motion, voice-over, müzik ve captions içeren explainer videoya dönüştüren bir agent skill’idir.

Neden yükseliyor · 79 günlük bir repo için 2046 yıldız dikkat çekici bir başlangıç sinyali; README’de örnek videolar ve uçtan uca iş akışı projeyi kolay anlaşılır kılıyor. Ancak son 28 günde commit ve farklı yazar bulunmaması, ilginin güncel geliştirme faaliyetiyle desteklendiğini göstermiyor.

[MM' 2026] Light-MER for efficient multimodal emotion recognition with sub-1B MLLMs.

Python SDK for LLM guardrails with safety classification, PII detection, prompt injection defense, and grounding checks. Protect AI applicat

CSS Animations on steroids.

Agent Skill that turns plain-English scene descriptions into AI-generated 3D models built live in Blender, via Alpha3D + Blender MCP. Works

Governed, provenance-sealed creative rendering for Databricks — a Streamlit App + Unity Catalog ai_render() function that turns any governed