Starred repositories
DFlash: Block Diffusion for Flash Speculative Decoding
The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.
Serve the home! Inference stack for your Nvidia DGX Spark aka the Grace Blackwell AI supercomputer on your desk. Mostly vLLM based for now and single-spark. For the not-so-rich buddies
Lightweight coding agent that runs in your terminal
llama-benchy - llama-bench style benchmarking tool for all backends
A framework for few-shot evaluation of language models.
Self-hosted GitHub Actions runner on Docker
System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge
An HTTP/1.1 client, written from scratch for Node.js
App for Claude Code / Codex / Gemini / OpenCode, vibe coding anytime, anywhere
Use Codex from Claude Code to review code or delegate tasks.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.
Xiaomi Home / MiOT CLI — manage smart home devices from the terminal
An agentic skills framework & software development methodology that works.
Official, Anthropic-managed directory of high quality Claude Code Plugins.
A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks …
Mexus is a local web console for managing multiple CLI AI Agent instances in parallel.
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
Run OpenClaw more securely inside NVIDIA OpenShell with managed inference
Miu2D is a 2D RPG game engine built with Rust + TypeScript + React + Canvas, designed for the Web platform. 剑侠情缘2/月影传说/新剑侠情缘网页复刻版
A dedicated effort to make an optimized, bleeding edge vLLM image using Docker to support DGX comprehensively
Complete guide to running Qwen3.5-35B-A3B on NVIDIA DGX Spark (GB10) with vLLM - installation, benchmarks, vision features, and troubleshooting
Build and run agents you can see, understand and trust.