Stars
The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.
A tool for exploring each layer in a docker image
⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs
Metadata-indexer and Viewer for AI-generated images
Free & OSS PostgreSQL RDS / DBaaS, Self-Host PG like a Pro
A curated list of useful resources that cover Offensive AI.
💽🕸 Postgres library to run WebAssembly binaries.
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Adding guardrails to large language models.
Resource list for generating JSON using LLMs via function calling, tools, CFG. Libraries, Models, Notebooks, etc.
a CLI that provides a generic automation layer for assessing the security of ML models
🤖 Build voice-based LLM agents. Modular + open source.
Collections of vector search related libraries, service and research papers
Build a chatbot or Q&A bot of your website's content
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
A tiny self-hostable Docker Registry facade - own your image URL without running your own registry
LlamaIndex is the leading framework for building LLM-powered agents over your data.
A workbench for writing toy implementations of distributed systems.
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
BTD - Bin To DNN: A DNN Executables Decompiler
A curated list of amazingly awesome Cybersecurity datasets
An easy-to-use federated learning platform
Automagically reverse-engineer REST APIs via capturing traffic
Pipy is a programmable proxy for the cloud, edge and IoT.