Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Guardrails, PII redaction, prompt-injection defense, interpretability and offensive/defensive AI security.
Signals: ai-safety, ai-security, guardrails, prompt-injection, jailbreak, llm-security, interpretability, explainable-ai
374 results
Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.
腾讯云智能渗透黑客松 Official repository of Tencent Cloud Intelligent Penetration Hackathon. Showcasing top open-source projects of LLM-based autonomous penetration agents, including multi-agent collaboration, automated penetration, AI-driven offensive security, and intelligent attack-defense solutions.
Completely block Google and its services
LinkStack - the ultimate solution for creating a personalized & professional profile page. Showcase all your important links in one place, forget the limitation of one link on social media. Set up your personal site on your own server with just a few clicks.
A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).
Set of tools to assess and improve LLM security.
This repository aims to map the ecosystem of artificial intelligence guidelines, principles, codes of ethics, standards, regulation and beyond.
[NeurIPS 2025] BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
A curated list of MLSecOps tools and resources for securing machine learning and AI systems - adversarial ML defense, LLM security, AI red teaming, model scanning, supply-chain protection, and MLOps pipeline security.
A Tox-based instant messaging and video chat client.
AIL framework - Analysis Information Leak framework. Project moved to https://github.com/ail-project
Library for training machine learning models with privacy for training data
Let's make an annoyance free, better open internet, altogether!
Algorithms to recover input data from their gradient signal through a neural network
A simple and accurate method to fool deep neural networks
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
🔐 Firewall Your Data, Control Agents. Prevent agent data exfiltration. Gain visibility into AI's interactions with your data / systems of record / existing software. https://discord.gg/tXjATaKgTV
Agent Security Bench (ASB)
The local runtime control layer for OpenClaw/Hermes-agent, PII & sensitive credentials protection.
SuperClaw: Red-Team AI Agents Before They Red-Team You
Keep your secrets hidden from AI agents.
Configurable Multi-layered AI Agentic Safety Framework
SlowMist Agent Security Skill: A comprehensive security review framework for AI agents operating in adversarial environments. Core principle: Every external input is untrusted until verified.
Jail your AI agent
24,535 repositories in the index in total.
