Havuz

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

Seedance 3 API developer guide and SDK project for AI video generation via MuAPI

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

AI agents are increasingly given real-world power — moving money, executing trades, taking actions with no human in the loop. But autonomy w

同一份提示词，两座汴京：Claude Opus 5.5 与 GPT 6 Sol 各自从零写出的《清明上河图》实时 3D 网页 · Same prompt, two cities — a real-time 3D Bianjing benchmark for LLMs

Visual AI video studio for MiniMax H3 + ComfyUI. Create text-to-video, image-to-video, reference video, video-to-video, storyboards, resumab

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

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

2026 Next-Gen AI Photo Background Remover & Object Removal Tool

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

Free, open-source plugin for Photoshop and ComfyUI, now on Adobe Exchange. Generate, inpaint, upscale, and split a flat image back into laye

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

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

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

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

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

514 Krea 2 Turbo prompts with generated examples and ComfyUI wildcards

Python SDK for vector search, semantic search, RAG, embeddings, and AI agents on Oracle AI Database

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;

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

Open-source, AI-native social media management, design & scheduling platform for 45+ channels. BYOK AI across 30+ providers with governance

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

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

TK Toolkit (formerly Anima Toolkit) — all-in-one Anima/SD toolkit for ComfyUI: LoRA manager (batch apply + Civitai metadata & downloads), Da

Ready-to-run examples showing NoPII PII protection with OpenAI, Anthropic, LangChain, LlamaIndex, and more

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

Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embe

AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessmen

[arXiv 2026] Code for "Elastic Token Compression for Pixel-Space Diffusion Transformers"

AIDrama Studio — Free AI-powered novel-to-video production platform with 20+ models (Kling, Seedance 2.0, FLUX, Veo). Self-hosted, MIT lic

A free, step-by-step roadmap from zero to AI engineer, built entirely from official Microsoft Learn content. Covers AI fundamentals, ML, gen

AI Agent plugin for Google NotebookLM (Claude, OpenClaw, etc) — generate slide decks, audio overviews, videos, mind maps, flashcards, quizze

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

Image generation CLI that reuses your Codex (ChatGPT) login.

An Agent Skill that turns raw text into production-ready, designer-grade posters in 20 visual styles. Supports Claude Code and Codex.

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

Dark, lime-accented one-page portfolio of Bharani Kumar S — an AI full-stack developer. Smooth-scrolling vanilla JS, SEO-ready, Resend conta

An open source, Native AI Gateway and LLM proxy built in Rust

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

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

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

Open-source, self-hosted platform to build, host, and chat with AI agents — LLM chat bots and image/video generation agents — from a single

AI Image Generator is a powerful and user-friendly desktop application designed to help creators produce stunning, high-quality artwork, pho

Free AI-powered learning resources, Masterclass Prompt Kits & practical training materials by MissAlpha™ AI Labs — covering AI Navigator, Ge

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

[ECCV 2026] WarpI2I: Image Warping for Image-to-Image Translation.

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

Run FLUX2 (klein, dev, base) or ZImage models natively in your Delphi , FPC or Lazarus IDE, written in pure pascal, no dependencies.

AI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII leakage, and adversarial attacks

A 24/7 AI-generated television channel. Bid credits to program the next slot, and call every clip REAL or AI.