Havuz

Free & Open Source AI Agent — Self-Hosted, Self-Learning, No Vendor API. Qwen2.5-7B + LoRA. 35 tools. Built on Islamic Epistemology (IHOS).

A next-generation AI-powered text adventure engine featuring dynamic storytelling, procedural world-building, and immersive visual/auditory

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

Evaan — a fully local, offline-capable AI companion chatbot built with Python & Hugging Face Transformers, running on Qwen2.5-0.5B-Instruct

开源可私有化的用户行为分析。Self-hosted user behavior analytics on ClickHouse and ClkLog. Events, funnels, retention, dashboards. AGPL-3.0.

Apache-2.0 reference backbone wrapping NVIDIA's Kimodo motion model behind MMCP. Run Kimodo on your own GPU.

Amazon Bedrock AgentCore enterprise platform accelerator with AWS CDK, Terraform organization guardrails, MCP/A2A agents, security, memory,

Production-ready RAG assistant for Moodle — containerized with Jenkins CI/CD on AWS.

A free, local AI image generation studio for Apple Silicon Macs. Run FLUX.2, Krea 2, Z-Image-Turbo, Qwen-Image-2.1-Turbo and SDXL offline on

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

Qwen3.8-27B on one laptop CPU: up to 2.52 token/s, 8 GB tested, no runtime accuracy loss. Native OpenAI-compatible API with function tools;

The best model under 200B at near 10 token/s exact batch throughput on a single laptop CPU, with an automatic 8 GB RAM path. Native C, no GP

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

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

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

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

Athena RAG Intelligence – AI-powered document intelligence platform with RAG, semantic search, source citations, voice assistant, analytics,

Codex AI game studio: 85 skills, 163 curated tools, Unity/Godot/Unreal/Blender workflows, img2threejs, reversible automation, and visual QA.

A free, open GenAI curriculum built from scratch. Start from zero, build real projects, and work your way up to production AI systems.

Hands-on LangChain learning repository covering Chat Models, Prompt Templates, Chains, RAG, Agents, and Tools with practical Python examples

Generative Models for Real-World Sensor Time Series

Humanlike — deterministic persona, context, memory and privacy controls for conversational AI agents · Детерминированное поведение ИИ-агенто

A self-hosted studio for pictures, videos and timelines, in front of your own ComfyUI.

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

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

Open-source Meta Muse video generator: no Muse video API yet, so MoonReel automates muse.ai for you. One idea in, a scripted, subtitled shor

Codex 短剧带货 Skill：salpx 生成分镜首帧，MiniMax H3 API 生成视频，支持美国市场本地化与剧本保真。

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

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

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

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

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

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

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

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

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

Generate images, video, audio and more via Civitai's orchestration API — a runtime-agnostic agent skill (AgentSkills format, zero deps, Node

Native macOS app for local AI image generation and editing on Apple silicon: Z-Image Turbo, Qwen-Image-2.1, Krea 2 Turbo, Anima Turbo and MO

Local web UI for h3.c — native Metal video/audio generation with MiniMax-H3 on Apple Silicon, no PyTorch or MLX required.

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

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

A fit-aware virtual try-on Flow-matching model trained on GarmentCodeVTONDataset.

把任意内容自动做成设计师级视频的端到端 skill:AI 写分镜 JSON,Remotion 渲染。8 步流水线:读取→定调→方向→分镜→配音→分段渲染→合成体检→导出。

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

AI powered whiteboards for AI-native companies

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

Smart component library for AI apps. With Chai UI, every AI model is controlled from one place, through a unified interface.

Sorca CM — colour editing, mixing, material layers and cutting inside Snapmaker Orca. Built on ChromaMatter, for Windows, Apple Silicon Mac

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

Full-stack AI short-drama pipeline with FastAPI, Pydantic structured outputs, ComfyUI and FFmpeg