Stars
The lightest AI sandbox. A process-based sandbox for Linux, no container, no VM, no privilege, no prompt injection
The factory for custom internal software, purpose-built for human2agent work.
Sandboxed devcontainer for running Claude Code in bypass mode safely. Built for security audits and untrusted code review.
⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
YARA signature and IOC database for my scanners and tools
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
Skills for AI Evals to compliment the course: AI Evals For Engineers & PMs
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
An open-source background agents coding system
The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.
The Systems Thinker's Deterministic Claude Code Control Plane
Sandbox any AI agent in seconds - zero setup, zero latency.
Algorithm powering the For You feed on X
Generate High-Quality Synthetics, Train, Measure, and Evaluate in a Single Pipeline
It is said that, Ilya Sutskever gave John Carmack this reading list of ~ 30 research papers on deep learning.
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require e…
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
The simplest, fastest repository for training/finetuning medium-sized GPTs.
safe harbor is a defensive mechanism for LLMs to self-defend against malicious input
Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we confi…
ai.go - ai is a shell hero, here to help whenever and wherever you need it.
IDA plugin which queries language models to speed up reverse-engineering
A Mixture‑of‑Experts Educational Framework for Adaptive Cybersecurity
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
A collection of learning resources for curious software engineers