AI, reviewed.

Google's open-source plugin: a deep-context agent drafts a design, then zero-context subagents review it to expose blind spots.

An open control surface that drives Claude Code, Codex, Cursor and other agents on your machine from a phone, browser or desktop app.

Google's end-to-end machine-learning framework for building, training and deploying models, strongest now in production, mobile and edge.

Product-Driven Development for coding agents: one git-tracked product model of entities, journeys and rules agents read instead of guessing.

HeyGen's Apache-2.0 renderer that turns HTML, CSS and seekable animation into MP4, with skills that teach coding agents to make videos.

Agent skill that draws 45 types of editorial diagram as one self-contained HTML and SVG file, styled to your brand.

The dominant deep learning framework: Python tensors and neural networks with strong GPU acceleration.

The standard Python library for defining, loading, training and running open models for text, vision and audio.

C/C++ engine for running LLMs locally on CPUs, Apple silicon and most GPUs, home of the GGUF model format.

Node-based interface and backend for running image, video and audio diffusion models locally.

Code for Sebastian Raschka's book on building a GPT-style LLM in PyTorch, step by step.

Rust vector database with fast filtered search, hybrid sparse-dense retrieval and quantization, self-hosted or managed.