The code
Trending implementations — one click from the idea behind each one.
🧠🎭 Face Swap Studio is a local macOS app for testing multiple face-swap models in one desktop workflow. It detects source and target faces, supports batch target selection, visual face mapping, model comparison, GFPGAN restoration, Real-ESRGAN upscaling, result previews, archive export, and temporary session cleanup.
Production-grade Multi-PDF RAG Intelligence System with FastAPI, Streamlit, LangChain, Gemini, ChromaDB, BM25, CrossEncoder, and RAGAS.
A full-stack Flask web application integrated with Google's Gemini API to dynamically summarize text content into multiple lengths.
An advanced semantic search and knowledge retrieval framework designed for academic research and intelligent information discovery.
Premium Apple-inspired portfolio showcasing AI products, intelligent systems, full-stack engineering, and product innovation including AuraOS and CareerOS.
Multi-agent AI system that analyzes financial reports, identifies risks, and generates executive summaries using LangGraph, RAG and LLMs.
Neural net to understand quantum computing
Open protocol for traversable knowledge networks. CBB traversal lets an 8B model match frontier AI on domain-specific queries.
Stop spending 3 days on one video. The AI workflow that cuts content creation from days to hours — YouTube, Blog, Podcast, Short-form
Interactive, in-browser visualization of how a transformer language model works: tokens, attention, quantization, and sampling, rendered live.
Sıfırdan ileri seviyeye Deep Learning yol haritası. 11 modül: PDF + Python + Jupyter Notebook. NumPy · TensorFlow · PyTorch karşılaştırmalı implementasyonlar.
LexAI v2 — Digital legal AI office. Next.js + Fastify + tRPC + Prisma.
Interview prep portal - dashboard, application tracker, interview prep, skills matrix, company research
A self-running fleet of AI agents that teaches its owner to think like an AI product manager - and maintains itself daily with no babysitting. Built on Claude Code.
Bi-temporal agent long-term memory: SQLite-backed MCP server with recall ranking, hybrid vector+FTS recall, and a source-staleness signal
🏥 AI-powered multi-disease early detection platform | Brain Tumor · Diabetic Retinopathy · Skin Cancer | PyTorch · FastAPI · React · Grad-CAM | B.Tech Major Project
Your agent has amnesia. Noshy fixes that. Persistent memory for AI agents — LLM extraction, hybrid search, zero deps.
🧠 FAANG-style technology intelligence platform leveraging autonomous AI agents and semantic search.
AI 導論（機器學習與深度學習概論）
This project adapts fablize's verified procedures — verification grounding, multi-story evidence gating, investigation protocol, and early-stop prevention.
Daily LLM value rankings - compare 300+ models by intelligence, speed and price. OpenRouter + Artificial Analysis. 大模型性价比排行榜
A practical guide to AI privacy, profiling, shadow profiling, local AI, cloud AI, and the future of human autonomy.
Claude Code plugin that delegates boring, low-risk tasks (bulk i18n, trivial style tweaks) to the Gemini CLI — a transparent Claude ⇄ Gemini pipeline.
10 legit ways to access major AI models (GPT, Claude, Llama, DeepSeek & more) for FREE — step-by-step guides, no subscription, no card.
The AI team that works 24/7 for one-person businesses — 50+ tools across 7 departments, built for solopreneurs
Guia de desarrollo y programacion con herramientas de Inteligencia Artificial y LLMS
End-to-end agentic quantum-ML pipeline: PennyLane GPU quantum-kernel anomaly detection + LangGraph multi-agent system + locally-hosted Qwen3-14B, benchmarked across network-intrusion, LHC physics, and fraud.
Local-first document AI. Run 100% locally by default, with API, CLI, and Web UI.
Implementation of Poly-attention, a higher-order self-attention proposed by Chakrabarti et al. of Columbia
Reference implementation of self-retracing agents.
A tiny, readable diffusion language model.
A library of well-typed tools for LLM agents.
Post-training quantization tools for transformers.
A starter kit for training vision-language models.
A from-scratch RLHF training loop in one file.
Implementations of many attention variants, benchmarked.
An extensible evaluation harness for LLMs.