Stars
Visa Vulnerability Agentic Harness
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & En…
klmbr - a prompt pre-processing technique to break through the barrier of entropy while generating text with LLMs
The automatic work journal/time tracker. Privately turns your screen into a timeline of what you actually accomplished. Open-source and local-first.
DSpark-style speculative decoding draft head for Qwen3.6-27B AEON: training recipe, paired eval harness, vLLM patches. +11% serve tok/s vs DFlash (all domains, CI'd).
A curated, non-BS library of the best resources for building and evaluating AI agents — papers, blogs, talks, tools, benchmarks. Maintained by BenchFlow.
DeepEP: an efficient expert-parallel communication library
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B c…
A large-scale language model for scientific domain, trained on redpajama arXiv split
Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code…
Turn the Hacker News front page into local AI art. Powered by mlx-vlm, MFlux, and Apple Silicon.
Easel is a Codex and Claude macOS workspace for AI-assisted product design and frontend iteration. It brings a local project library, design-system setup, Codex chat, a live web preview with a poin…
Agent skill for elegant and simple html plans, architecture diagrams, or whatever else you can think of.
Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.
Fast LLM speculative inference server for consumer hardware.
Analyze AI agent trajectories: extract actions, summarize, embed, and visualize.
macOS menu bar app that tells you, in plain English, what each USB-C cable plugged into your Mac can actually do
World’s single largest Internet domains dataset
Lossless DFlash speculative decoding for MLX on Apple Silicon
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.
A tool used to make user-friendly wine wrapped ports of Windows software for macOS.
Place to keep various projects related to AI computing
A curriculum for learning about gpu performance engineering, from scratch to what the frontier AI labs do