Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

wp2shell (CVE-2026-63030 & CVE-2026-60137) - full RCE chain

MeTr (metric trees)

Git. Ship. Done - Core

Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

AI skills to be used with Qonto

FFMPEG with NDI support

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

13F × Form 4 · confluence

Audio Tools (a powerful Audio library for Arduino, PlatformIO, IDF)

LLM training in simple, raw C/CUDA

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini C…

An app that brings language models directly to your phone.

Gas Town - multi-agent workspace manager

a WebMIDI companion app for the Zoom LiveTrak L6

AutoTune UGen for SuperCollider

Claude Code orchestrator in one window

A collection of DESIGN.md files analysis by popular brand design systems. Drop one into your project and let coding agents generate a matching UI.

💅🏻 ⚒ A collection of awesome design systems

Ghidra is a software reverse engineering (SRE) framework

The agent-first database

🎚️ Open Source Audio Matching and Mastering

Anthropic's educational courses

An embedded, active, neuroscience-inspired memory system for AI agents

minimal/tiny open-source/DIY shield for Raspberry Pi boards, providing hardware compatibility with the norns ecosystem.

Private Monero + Tari merge mining — the whole stack in one command: full node, P2Pool, XvB optimizer, and a live dashboard, all behind Tor.