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
381 results
A lightweight, stable, and performance-focused customized version of Windows that enhances privacy and compatibility
TrackerControl Android: monitor and control trackers and ads.
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.
Manage your photos with Piwigo, a full featured open source photo gallery application for the web. Star us on Github! More than 200 plugins and themes available. Join us and contribute!
Your web application for managing personal data.
Self-hosted, Node.js based analytics tool for those who care about privacy.
Think fearlessly with end-to-end encrypted notes and files. For issues, visit https://standardnotes.com/forum or https://standardnotes.com/help.
A self-hosted, ad-free, privacy-respecting metasearch engine
Firefox privacy, security and anti-tracking: a comprehensive user.js template for configuration and hardening
KeePassXC is a cross-platform community-driven port of the Windows application “KeePass Password Safe”.
🕵️♂️ All-in-one OSINT tool for analysing any website
AI on the way. An auto deep learning pipe dream. An RDBMS approach to deep learning. Declarative, explainable, scalable, optimizable, easy to deploy, all that good stuff.
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.
Interpretability and explainability of data and machine learning models
Deep learning based content moderation from text, audio, video & image input modalities.
Transparent anonymization proxy for AI-assisted pentesting. Strips IPs, credentials, hostnames and PII before they reach any LLM (Claude, OpenAI, OpenRouter). Local Ollama + regex detection. Per-engagement vault.
Library for training machine learning models with privacy for training data
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.
alpha-beta-CROWN: An Efficient, Scalable and GPU Accelerated Neural Network Verifier (winner of VNN-COMP 2021, 2022, 2023, 2024, 2025)
Algorithms to recover input data from their gradient signal through a neural network
A simple and accurate method to fool deep neural networks
AI-powered vulnerability scanner extension for Burp Suite with multi-provider support (Ollama, OpenAI, Claude, Gemini)
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
24,523 repositories in the index in total.
