A C# inference engine for running large language models (LLMs) locally using GGUF model files. TensorSharp provides a console application, a web-based chatbot interface, and Ollama/OpenAI-compatibl…

high-performance linear attention kernel library built on TileLang

Skills for Real Engineers. Straight from my .claude directory.

LLM inference engine written in .NET

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Use Codex from Claude Code to review code or delegate tasks.

🌀 OpenAPI to TypeScript codegen. Production-grade SDKs, Zod schemas, TanStack Query hooks, and 20+ plugins. Used by Vercel, OpenCode, and PayPal.

Easily sync code to a remote machine and run commands there. That's it.

Vercel's official collection of agent skills

Daily cat pictures on your home assistant server

ComfyUI for NVIDIA GPU in a Docker container with user configurable uid/gid

Beads - A memory upgrade for your coding agent

Conductor is a Gemini CLI extension that allows you to specify, plan, and implement software features.

Autonomous multi-session AI coding

Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.

Get 10X more out of Claude Code, Codex or any coding agent

omo; the best agent harness - previously oh-my-opencode

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.

Interactive, editable docs designed for coding agents

The world's most powerful open-source bio AI assistant - Access academic literature, clinical trials, drug labels, and more, all through natural conversation.

The Complete Claude Code CLI Guide - Live & Auto-Updated Every 2 Days

100+ AI Agent & RAG apps you can actually run — clone, customize, ship.

Build reliable Gen AI solutions without overhead 🍕

Welcome to the official repository of SINQ! A novel, fast and high-quality quantization method designed to make any Large Language Model smaller while preserving accuracy [ICML 2026]

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

An open-source AI agent that brings the power of Gemini directly into your terminal.

Code that helps to write logic based on SIMD operations

Code that helps to write logic based on SIMD operations