🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

Scripts for agents, shared between my repositories.

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Control panel for VLLM, Sglang, llama.cpp, exllamav3

Profile repo — categorized index of NVFP4 model releases, DGX Spark inference stacks, Apple Silicon MLX builds, the voice-AI stack, and the AEON Media Production toolchain · ☕ Tips welcome

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…

Yocto Linux project to build a complete mainline Linux-based firmware for the Centauri Carbon printer

Exploration, Research and Development of extensions to the Centauri Carbon printer from Elegoo

Structured Chain-of-Thought

Lossless abliteration of Qwen3.6-27B with NVFP4 hardware quantization for DGX Spark / Blackwell. BF16 (51 GB) + NVFP4 (26 GB) deployment guide, docker-compose, and QuickStart.

Self-host Honcho memory layer for Hermes Agent — OpenRouter + Venice, no code changes

Fast LLM speculative inference server for consumer hardware.

Lightweight Python tool using Optuna for tuning llama.cpp flags: towards optimal tok/s for your machine

Hermes Agent 从入门到精通 · 橙皮书系列 · Nous Research 开源 AI Agent 框架实战指南

Connect Your Agents And Harnesses With Any Provider 🦚

Opus 4.6 Telegram AI assistant via Claude Max + OpenClaw. One-click setup.

opencode mac utility

Desktop Companion for Hermes Agent

Open source CLI agent that generates complete lesson bundles in your teaching voice. 48+ tools, zero-touch 9-file output, local-first privacy.

Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!

autonomous harness engineering

Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon

LLM inference in C/C++

A pixel art space shooter built entirely by a 9B AI model on a single RTX 3060. Zero hand-written code.

TUI consciousness monitor for Hermes

Agent memory infrastructure: provenance, rollback, lifecycle/supersession, three-layer model (working memory + session archive + wiki). Markdown on disk, MCP-native.