Projects sharing features with Deepteam

PyRIT is an AI vulnerability assessment tool and security scanner designed to detect risks in large language model applications. It functions as a generative AI red teaming framework used to simulate adversarial attacks and identify weaknesses in system guardrails. The tool automates AI risk assessment by scanning generative AI components for security vulnerabilities. It utilizes automated testing and analysis to identify security gaps and prevent potential exploits through a consistent, repeatable process. The system incorporates asynchronous model orchestration to compare security postures

Garak is a suite of tools for measuring AI reliability, scanning for vulnerabilities, and automating security assessments through adaptive probing. It functions as a generative AI vulnerability scanner and evaluation tool designed to identify security gaps, hallucinations, and failure modes in language models. The framework provides a toolkit for red-teaming and safety assessments, utilizing a structured system of probes and detectors to calculate failure rates. It specifically scans for risks such as data leakage and prompt injection by recording model responses to adversarial inputs. The p

Promptfoo is an evaluation framework designed for testing, benchmarking, and red-teaming language models and agentic workflows. It provides a unified environment to run prompts against multiple providers, allowing developers to systematically validate model outputs against objective assertions, semantic similarity metrics, and custom grading rubrics. The platform distinguishes itself through a provider-agnostic execution layer and a stateful orchestrator capable of simulating multi-turn conversations and complex tool-use trajectories. It includes a dedicated adversarial mutation pipeline that

Garak is an AI model evaluation tool and vulnerability scanner designed for red teaming large language models and auditing the security of retrieval-augmented generation pipelines. It identifies behavioral weaknesses, such as jailbreaks, hallucinations, and data leakage, by simulating adversarial attacks and executing automated testing vectors. The framework utilizes an adaptive probing loop where prompts can react to previous model behavior and be modified in flight via middleware. To ensure consistent analysis, it employs a provider-agnostic interface to interact with various model APIs and

PurpleLlama is a collection of security components and toolkits designed for large language models. It provides specialized systems including a code security scanner, a content moderation system, a prompt injection firewall, and a security assessment toolkit. The project enables the identification and blocking of jailbreaking attempts and malicious prompts during model inference. It includes capabilities for detecting violating content across multiple languages and modalities and scanning generated code for vulnerabilities to prevent the execution of insecure commands. The framework further

The Adversarial Robustness Toolbox (ART) is an open-source library that provides a unified framework for evaluating, defending, and certifying machine learning models against adversarial threats. It wraps models from any framework behind a common estimator interface, enabling composable pipelines for attack generation, defense application, robustness certification, and privacy auditing across evasion, poisoning, and extraction threats. The library distinguishes itself by covering the full adversarial ML security lifecycle within a single toolkit. It supports gradient-based adversarial example

This project is a framework for generating synthetic tabular data that preserves the statistical properties and relational integrity of original source datasets. It functions as a metadata-driven engine, utilizing language models to synthesize information even when original training samples are restricted. The system is designed to maintain logical consistency across complex, multi-table structures while ensuring that generated outputs adhere to defined schema requirements. The platform distinguishes itself through a focus on privacy-preserving synthesis, integrating tools to quantify and mit

Keyguard is a password manager application and secure vault designed for storing and organizing logins, passkeys, and sensitive data. It provides a multi-factor authentication vault that utilizes encrypted offline access to ensure credentials remain available without an internet connection. The application includes a dedicated SSH key manager and agent integration for generating and managing keys to access remote servers. It also features a password security auditor that analyzes vault entries to identify compromised, reused, or weak credentials. The system covers a broad range of security c

Security oriented helper functions for Elixir

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP servers for tool poisoning.

zsh plugin to manage 1password

A master checklist for securing your online life.

🍍Jeff provides the simplest way to manage web sessions in Go.

v2rayNG is an Android proxy client designed to route device network traffic through encrypted tunnels. It functions as a network routing engine that intercepts outgoing requests and applies custom traffic rules to manage connectivity and enhance user privacy. The application distinguishes itself by integrating a high-performance network proxy core, which enables complex protocol translation and traffic management directly on mobile devices. It utilizes local loopback and Unix-socket tunneling to redirect device-wide requests, maintaining persistent connectivity through native background servi

Flower is a federated learning framework and distributed machine learning orchestrator designed to train models across decentralized devices. It functions as a privacy-preserving toolkit that enables model training and data analysis on local hardware, ensuring raw data remains on the device while contributing to a synchronized global model. The system employs an agnostic wrapper and integrator to connect diverse machine learning libraries, allowing different frameworks to operate within the same training loop. It uses a remote procedure call orchestrator to manage the exchange of model weight

Amnezia Client is a cross-platform VPN client application and server orchestrator designed to manage secure tunnels and automate the deployment of containerized VPN services on remote self-hosted servers. It functions as a multi-protocol VPN manager that supports various tunneling standards to ensure connectivity across restrictive network environments. The project distinguishes itself through network traffic obfuscation, which disguises VPN traffic as common web protocols or DNS requests to bypass deep packet inspection and censorship. It further enables the automation of remote server admin

| 🔥 News | 🤖️ Demo | 🚀 Quick Start | 💾 Benchmark | 📖 Docs |

Plugin to update known hosts automatically if needed

Easily create and manage your addy.io aliases, recipients and more from your phone, tablet or wearable with this gorgeous addy.io app for Android.

JSON Web Token library for C++

A web application featuring some handy password tools

Authelia is a centralized identity and access management server designed to secure web applications through unified authentication and authorization. It functions as an identity authority that enables single sign-on across diverse platforms, allowing users to access multiple services with a single set of credentials. By acting as a standards-compliant provider, it facilitates secure identity propagation and token issuance for client applications. The platform distinguishes itself through its ability to integrate directly with web gateways as a reverse proxy authentication middleware, intercep

SpiceDB is a distributed permission store and relationship-based access control system. It provides a scalable database for storing and querying fine-grained authorization relationships, implementing a consistency model inspired by Google Zanzibar to manage access rights across large-scale applications. The system uses a dedicated schema language to define the rules and logic governing how relationships translate into permissions independently of application code. It functions as a pluggable authorization engine that persists relationship tuples in external relational databases such as Postgr

A dead simple, highly performant, highly customizable sessions middleware for go http servers.