Visa Vulnerability Agentic Harness

OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security

Google Cloud Knowledge Catalog Tools and Samples

The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.

Companion code for the global workspace interpretability paper

Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

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

World's First Full-Chinese Ray-Ban Meta AI Assistant - 全球首个全中文 Ray-Ban Meta 智能眼镜 AI 助手

Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.

Chrome DevTools for coding agents

An agentic skills framework & software development methodology that works.

Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.

Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

A collection of links related to Linux kernel security and exploitation

TuSK is a virtual TPM based FIDO2 Security Key

A pure Rust implementation of FIDO2/WebAuthn CTAP 2.0/2.1/2.2 protocol

agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.

autonomous open source ai lab

This project aims to provide a central repository for many useful Tsunami Security Scanner plugins.

OSV-SCALIBR: A library for Software Composition Analysis

Vulnerability scanner written in Go which uses the data provided by https://osv.dev

Awesome List for Agentic RL

OWASP Autonomous Penetration Testing Standard

AI Smart Contract Security Analysis and PoC Generation Framework

Autonomous vulnerability discovery and exploit validation.

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

Autonomous multi-agent CVE analysis on Android. No cloud. No GPU. No API key. MNN + Qwen in Termux. BLAKE3 tamper-proof logs. Config-driven. 300€ phone.

Adaptive Test-time Learning and Autonomous Specialization

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