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
370 results
No description
Claude Code 逆向工程研究仓库
SeClaw provides a practical foundation for measuring, diagnosing, and comparing security failures in autonomous LLM agents.
LLM privacy gateway in Go — millisecond-latency PII and secret redaction. Used in production by PackyCode.
Powerful search page powered by LLMs and SearXNG
The automated prompt injection framework for LLM-integrated applications.
Redteaming LLMs using other LLMs
Dropbox LLM Security research code and results
AI / LLM Red Team Field Manual & Consultant’s Handbook
AI-native automated software risk analysis skill. LLM-driven, Code-First approach for comprehensive security risk assessment, threat modeling, security testing, penetration testing, and compliance checking.
Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours
Open-source LLM red-teaming technique toolkit (162 transforms, 36 mutators, 25 tool surfaces). MIT.
Lightweight LLM firewall: masks PII, routes calls, leaves zero trace.
Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!
This repository provides a benchmark for prompt injection attacks and defenses in LLMs
sharing NEW strong AI jailbreaks of multiple vendors (LLMs)
[ICML 2024] Binoculars: Zero-Shot Detection of LLM-Generated Text
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]
No description
A template for building LLM-based AI text adventure games, with LLM prompt injection theme as an example story.
No description
Observe how memory shapes an answer. Pensieve is an interactive system for visualizing, interpreting, and managing how Large Language Models (LLMs) “remember” a user. It bridges the gap between model-level mechanisms and user-level understanding, making AI memory observable, explainable, and partially controllable.
[ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models".
Course Materials for Interpretability of Large Language Models (0368.4264) at Tel Aviv University
24,545 repositories in the index in total.
