Learn Anything about AI in one site

nanoGPT is the simplest, fastest repository for training/finetuning medium-sized GPTs. It is a rewrite of minGPT that prioritizes practicality over education. Still under active development, but currently the file train.py reproduces GPT-2 (124M) on OpenWebText, running on a single 8XA100 40GB node in about 4 days of training.

Built to make you extraordinarily productive, Cursor is the best way to code with AI.

KTransformers is a flexible framework for experiencing cutting-edge optimizations in LLM inference and fine-tuning, focusing on CPU-GPU heterogeneous computing. It consists of two core modules: kt-kernel for high-performance inference kernels and kt-sft for fine-tuning. The project supports various hardware and models like DeepSeek series, Kimi-K2, achieving significant resource savings and speedups, such as reducing GPU memory for a 671B model to 70GB and up to 28x acceleration.

MCP server that injects up-to-date, version-specific documentation and code examples into LLM prompts.

BettaFish (Weiyu) is an open-source multi-agent sentiment analysis system built from scratch without relying on any frameworks. It enables users to analyze public opinion across 30+ major domestic and international social media platforms and millions of comments through chat-like interactions, breaking information silos, revealing true sentiments, predicting trends, and aiding decision-making. Key features include AI-driven global monitoring, multimodal analysis, agent forum collaboration, and lightweight, extensible deployment.

Spec Kit is an open-source toolkit designed to enable Spec-Driven Development, helping developers create high-quality software by focusing on detailed specifications and leveraging AI coding agents for efficient implementation.

Google Antigravity is an innovative AI-powered integrated development environment (IDE) from Google, designed as an agent-first platform that enables autonomous AI agents to plan, code, and verify complex software tasks using advanced models like Gemini 3.

Open-source Python library from Hugging Face that supplies thousands of pretrained transformer models and utilities for text, vision, audio and multimodal tasks.

A cloud-based API that lets developers integrate OpenAI’s cutting-edge language, image, and audio models into their own products via simple RESTful endpoints.

Claude is a next generation AI assistant built by Anthropic and trained to be safe, accurate, and secure to help you do your best work. Create with Claude.

Elo-style leaderboard where millions of crowd votes rank AI chatbots via blind head-to-head “battle mode” comparisons.

vLLM is a high-throughput, memory-efficient inference and serving engine for large language models (LLMs), built to deliver state-of-the-art performance on GPUs with features such as PagedAttention and continuous batching.