A desktop application (built with Tkinter + ttkbootstrap) automatically turns a folder of images into a quiz. It was generated using GPT-5.2 via GitHub Copilot and is open for public use.

Arianna Method — non-anthropocentric AI ecosystem. AI is not a tool.

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

High-speed Large Language Model Serving for Local Deployment

like Karpathy, but micro: a live autopsy on your innoncent prompts

Your Personal AI super intelligence. Private, Simple and extremely powerful.

🚀✨ Help beginners to contribute to open source projects

A package build system for Termux.

phone-2 (Galaxy A07 4 GB Termux) ecosystem — small intelligence + emergence in pocket. Janus 170M / Resonance 200M with persona presets, AML field-physics, notorch micro-training, mesh-agent slots.

neural networks in pure C

Termux cpu usage without root

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 utility for managing installations of the Linux distributions in Termux.

Janus-Series: Unified Multimodal Understanding and Generation Models

Chronos: Pretrained Models for Time Series Forecasting

Termux - a terminal emulator application for Android OS extendible by variety of packages.

The knowledge compiler. Raw sources in, interlinked wiki out. Inspired by Karpathy's LLM Wiki pattern.

PITOMADOM — Hebrew Root Resonance Engine. Janus Architecture

A 3D raymarched virtual pet companion for Pi CLI

A curated list of Israeli-made projects, events, and individuals

📻 A super tiny WAVE parser and decoder, without any dependencies or unnecessary abstraction layers

Hierarchical Reasoning Model Official Release

The first port of karpathy/microgpt to an array language. Dyalog APL, explicit matrix gradients, no autograd.

LLaDA is a diffusion model for natural language that, unlike traditional autoregressive models, learns to model the distribution of text through a process of progressive data masking and its invers…

👀「大模型」2小时从0训练65M参数的视觉多模态VLM！Train a 65M-parameter VLM from scratch in just 2h!

🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!