CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.

Curated coding interview preparation materials for busy software engineers

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

SGLang is a high-performance serving framework for large language models and multimodal models.

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

Open source alternative to AWS. Elastic compute, block storage (non replicated), firewall and load balancer, managed Postgres, K8s, AI inference, and IAM services.

Contexts Optical Compression

An open, programmable decision layer for models and compute.

The easiest, and most secure way to access and protect all of your infrastructure.

Fast and memory-efficient exact attention

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…

High-performance data engine for AI and multimodal workloads. Process images, audio, video, and structured data at any scale

Composable, accessible components with thoughtful defaults. Build your own component library with code you can customize, extend, and make your own.

The Patterns of Scalable, Reliable, and Performant Large-Scale Systems

Tracking urban growth by comparing satellite images over time and visualising changes on a map.

An extremely fast Python package and project manager, written in Rust.

OCR, layout analysis, reading order, table recognition in 90+ languages

Convert PDF to markdown + JSON quickly with high accuracy

Realtime RAG Chatbot Project for Finance.

A high-throughput and memory-efficient inference and serving engine for LLMs

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Serve high throughput and scalable LLM using Ray and vLLM

An orchestration platform for the development, production, and observation of data assets.

FastAPI Tips by The FastAPI Expert!

FastAPI Best Practices and Conventions we used at our startup

This is a project at class IT3160E Intro to AI at HUST

Chat with multiple PDFs locally

Full-stack web application template with FastAPI, React, SQLModel, PostgreSQL, Vite, Tailwind CSS, shadcn/ui, FastAPI Cloud, and Docker Compose.

Simple Implementation of Stable Diffusion from scratch