Intelligent web vulnerability analysis suite leveraging Generative AI for developers, pentesters, and security researchers.

CTF challenges designed and implemented in machine learning applications

A curated list of awesome leaderboard-oriented resources for AI domain

Democratizing Reinforcement Learning for LLMs

open-source coding LLM for software engineering tasks

All Cursor AI's official download links for both the latest and older versions, making it easy for you to update, downgrade, and choose any version. 🚀

[ACL 2024] ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

Spec-driven development for AI coding assistants.

🔮Reasoning for Safer Code Generation; 🥇Winner Solution of Amazon Nova AI Challenge 2025

Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.

Tools for checking ACL paper submissions

[ICLR 2025 Spotlight] The official implementation of our ICLR2025 paper "AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs".

Source code for LLMxCPG paper

This repository provides a benchmark for prompt injection attacks and defenses in LLMs

[ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).

[ICLR 2025] Dissecting adversarial robustness of multimodal language model agents

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

Awesome List for Agentic RL

Cybersecurity AI (CAI), the framework for AI Security

Public Source code Release of Theori's AIxCC AFC Submission

BandFuzz is a collaborative fuzzing framework designed to optimize performance. BandFuzz uses reinforcement learning algorithms to schedule fuzzing instances in real-time.