Havuz

Official codebase for the paper "How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance" (ICML 2026).

Official Implementation of LongLive-RAG: A general retrieval-augmented framework for long video generation.

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

Official Code for GPIC: A Giant Permissive Image Corpus for Visual Generation

Open-source AI GEO (Generative Engine Optimization) auditor — production-ready Next.js SaaS that checks how well landing pages are cited by

AI画布、AI短剧创作工具：免费、轻量的无限画布，支持短剧剧本、角色管理、分镜、图像/视频生成和短剧剪辑，集成 ComfyUI、Agent、MCP。Free AI canvas and short drama maker.

AI-powered pre-production canvas for filmmakers. Flagship models, infinite canvas, auto-export.

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

The open-source alternative to Suno and ElevenLabs Music. Natural language music composition, run locally, own everything.

SparkWork is a local-first desktop Agent workbench for professional development and complex work. Orchestrate workflows, collaborate across

Open-source AI social media post generator — production-ready Next.js SaaS with live platform mockups for LinkedIn, Twitter/X, Instagram, Fa

AI presentation engine. Describe your deck and the look, it derives a bespoke style and renders polished 1920x1080 HTML slides with real cha

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

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

Open-source AI product photography studio for Amazon sellers — production-ready Next.js SaaS with multi-image reference upload, preset templ

Generative image and video runtimes for Apple Silicon (MLX): text/image-to-image, instruction editing, masked edit, text/image/reference-to-

This is a comprehensive tool for merging, analyzing, and training Anima models (cosmos) in a hierarchical (layer-by-layer) manner.Multilingu

Open-source AI knowledge base & custom chatbot builder — production-ready Next.js SaaS with RAG, document upload, URL scraping, Q&A training

Open-source AI virtual try-on tool — production-ready Next.js SaaS that fits garments onto any person photo. Free Botika & Lalaland alternat

Open-source AI blog writer & SEO content CMS — production-ready Next.js SaaS with rich text editor, folder categorization, AI generation, an

Open-source AI virtual home staging tool — production-ready Next.js SaaS that turns empty rooms into furnished showrooms with photorealistic

3x more usage on your coding agent, same quality. Have an multi-agent setup in mind? Bello already supports it. Mix models, run agents in pa

AI film-production skill pack for Claude Code and OpenAI Codex: 11 creator-* skills from screenplay to final cut, with a recorded production

edge-dit.cpp — a native C/C++ inference engine for Diffusion Transformers (DiT), designed for local and resource-constrained devices with au

Companion code for the Manning book 'LLM Customization and Fine-Tuning.' Adapt open-weights LLMs end to end: prompting and RAG, LoRA/QLoRA,

[NeurIPS 2026] Official implementation of Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion

Open-source AI pipeline for short-form commerce videos: multimodal analysis, RAG scripts, multi-agent orchestration, FFmpeg composition, and

Paste your code and get brutally roasted by AI — then refactored into something actually worth shipping.

Open-source AI old photo restoration tool — production-ready Next.js SaaS that colorizes, denoises, and repairs damaged vintage photos. Free

短视频解析 · AI 剧本复刻 · 一键成片 | LangGraph 多 Agent 流水线

A production-grade control layer that sits between your application logic and any LLM — input validation, schema enforcement, circuit breaki

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

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

Open-source node-based AI media studio — generate image, video & music on an infinite canvas, or let an AI agent build a whole short film fr

A lightweight LLM evaluation layer that turns subjective model outputs into deterministic decisions by scoring attribution, specificity, rel

Zero-skill cinema. Senior-director prompts on autopilot. A Claude Code Skill for high-quality AI image / video / music prompt crafting and b

Automated Chinese AI daily publisher that turns structured agent-generated reports into searchable, archived GitHub Pages HTML pages.

HTML Anything, yerel coding-agent CLI’larını kullanarak HTML içerik ve tasarım üretmeyi, önizlemeyi ve farklı formatlara aktarmayı sağlayan bir editördür.

Neden yükseliyor · 139 günde 8.954 yıldıza ulaşması belirgin ilgi gösteriyor; yerel agent oturumlarını kullanma, API key gerektirmeme ve çok sayıda hazır çıktı şablonunu tek arayüzde sunma vaadi dikkat çekici. Ancak ilginin kaynağı kesin olarak bilinmiyor ve son 28 gündeki 1 commit ile 1 farklı yazar, mevcut yıldız ivmesinin geliştirme aktivitesiyle desteklendiğine dair sınırlı kanıt sunuyor.

Plug-and-play JSON style prompts for Nano Banana Pro, GPT Image & Midjourney. Copy one style.json, get a consistent look. New styles every w

Conteúdo em PT-BR para a AWS AI Practitioner (AIF-C01), com foco em fundamentos de IA/ML na AWS, serviços gerenciados (Bedrock, Sagemaker, e

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

The most complete MCP server for Blender 🧊 — 223 tools so any AI agent (Claude Code, Cursor, opencode, Antigravity) can model, texture, ligh

(ICML 2026) IDLM: Inverse-distilled Diffusion Language Models

Open-source, self-hostable alternative to ChatGPT and NotebookLM — agents, skills, MCP, and cited knowledge in one AI workstation. Your mode

Drive Google Flow from the command line: Veo video and Imagen images, scripted, batched and pipeline-ready. Ships an MCP server so coding ag

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

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

A full-stack AI prompt library for discovery, structured authoring, safe imports, moderation, and shareable agents.

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

Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic m