USB2 core for LiteX

Winner at MIT Hard Mode 2026. Lets AI control the human body via EMS to help you learn.

Qt-based digital signal analyzer, using Suscan core and Sigutils DSP library

Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat.

Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

Hobby operating system for vintage 32-bit PCs

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

Sudoless Apple Silicon system monitor (native SwiftUI GUI) with ANE / Media Engine / memory-bandwidth tracking

File-based orchestration for a fleet of long-lived Claude Code workers.

LHCb/WCT analysis kit for log-periodic residuals, active-domain winding, Koide-like comb geometry, and sideband controls in B0 → K*0 μ+μ− open data.

Every API has a secret identity. This finds it, absorbs every feature from every competing tool, then builds the GOAT CLI — designed for AI agents first, with SQLite sync, offline search, and compo…

Build product integrations with AI.

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

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

Token efficient Claude Code full Python rebuild. AI Coding Agent in 270K LoC pure Python. Up to 200X Cost Saving!

The batteries-included agent harness.

A straightforward method for training your LLM, from downloading data to generating text.

Fast and memory-efficient classical machine learning operators

Graph Convolutional Network (GCN) for Research Paper Classification

A modular, end-to-end GNSS receiver simulator in Python that models satellite signal generation, propagation effects, receiver processing, and position estimation using pseudorange measurements and…

High-performance computer vision primitives in pure C99. Zero dependencies, pluggable allocator, SIMD-ready layout. Built for edge deployment and FFI.

Pure-C federated learning library for MCU-class edge devices over LoRa. STM32 + SX1276.

Minimal real-time OS for STM32H7, built from scratch for edge ML inference and on-device training

MINERVA - Minimal Inference Engine for Robust, Verifiable, and Authenticated ML. Encrypted, integrity-verified neural network inference for MCUs down to ATmega328P.

The World's First Unified Virtual Filesystem For AI Agents

A modified markdown file capable of holding and referencing semantic data

Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more