The project code for the Overhearing Agents project (AI Agents Workshop @ COLM 2025).

Improved techniques for optimization-based jailbreaking on large language models (ICLR2025)

Code for the paper "Defeating Prompt Injections by Design"

Flow Integrity Deterministic Enforcement System. Mechanisms for securing AI agents with information-flow control.

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.

A fast + lightweight implementation of the GCG algorithm in PyTorch

Universal and Transferable Attacks on Aligned Language Models

An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)

🚀 The fast, Pythonic way to build MCP servers and clients

mcptee - tool for MCP developers to log stdin transport

DoomArena is a Framework for Testing AI Agents Against Evolving Security Threats

A curated list of resources about AI agents for Computer Use, including research papers, projects, frameworks, and tools.

Autonomous Agents (LLMs) research papers. Updated Daily.

SafeArena is a benchmark for assessing the harmful capabilities of web agents

🌎💪 BrowserGym, a Gym environment for web task automation

Two conversational AI agents switching from English to sound-level protocol after confirming they are both AI agents

AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.

AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM

Papers and resources related to the security and privacy of LLMs 🤖

Python tool for converting files and office documents to Markdown.

TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle

Interactive Tables and Data Grids for JavaScript

💩🚀 Windows 95 in Electron. Runs on macOS, Linux, and Windows.

A curated list of trustworthy deep learning papers. Daily updating...

📂 Web File Browser

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

Locally run an Instruction-Tuned Chat-Style LLM

Aligning pretrained language models with instruction data generated by themselves.

🦜🔗 Build context-aware reasoning applications

A framework for the evaluation of autoregressive code generation language models.