AI, reviewed.

Anthropic's open-source sandbox behind Claude Code's /sandbox: it fences any process off from your files and network.

A security firm's audit methods, packaged as 46 plugins for Claude Code and Codex.

Anthropic's Claude Code plugin that reviews what Claude writes three times: on every edit, at the end of every turn and on every commit.

NVIDIA's runtime that puts each AI agent in its own sandbox and checks every file, system call and connection against a policy.

Stacklok's platform that runs each MCP server in its own locked-down container, with access policy and audit logs for teams.

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.