Repository History
38 repositories tagged with security
ECC: The Agent Harness Performance Optimization System for LLMs
ECC is an advanced agent harness performance optimization system, providing a coordinated engineering system and toolbox for LLM development. It enables agents to plan, test, implement, review, and learn effectively, enhancing productivity and security for AI-driven coding workflows across platforms like Claude Code, Codex, and Cursor.
Agent Governance Toolkit: Policy Enforcement for Autonomous AI Agents
The Microsoft Agent Governance Toolkit (AGT) provides robust policy enforcement, zero-trust identity, and execution sandboxing for autonomous AI agents. It addresses critical security and compliance challenges, ensuring agents operate within defined boundaries and providing tamper-evident audit trails. AGT covers all 10 items of the OWASP Agentic Top 10, making it essential for shipping AI agents to production securely.
gh-aw-firewall: Secure Your Agentic Workflows with a Network Firewall
gh-aw-firewall is a robust network firewall designed specifically for agentic workflows, restricting outbound HTTP/HTTPS traffic to an allowlist of domains. It operates by running commands within a Docker sandbox, leveraging a Squid proxy for traffic filtering and an optional API proxy sidecar to securely manage LLM API keys. This project is a crucial component of GitHub's ongoing exploration into Agentic Workflows, enhancing their security and control.
OpenSandbox: A Secure and Extensible Sandbox Runtime for AI Agents
OpenSandbox is a powerful, general-purpose sandbox platform designed for AI applications. It provides secure, fast, and extensible runtime environments, supporting multi-language SDKs and Docker/Kubernetes deployments. This project is ideal for developing and evaluating AI agents in isolated, controlled settings.
CubeSandbox: Instant, Concurrent, and Secure Sandbox for AI Agents
CubeSandbox, developed by TencentCloud, is a high-performance, secure sandbox service built on RustVMM and KVM, designed specifically for AI agents. It offers ultra-fast startup times, hardware-level isolation, and high-density deployment, making it ideal for scalable and secure agent execution environments. The service is also fully compatible with the E2B SDK for seamless integration.
Destructive Command Guard (dcg): Protecting AI Agents from Dangerous Commands
The Destructive Command Guard (dcg) is a high-performance hook designed to prevent AI coding agents from executing dangerous git and shell commands. Built in Rust, dcg intercepts and blocks catastrophic operations like `git reset --hard` or `rm -rf`, offering clear explanations and safer alternatives. It provides a crucial safety layer for developers working with tools like Claude Code, Codex CLI, and GitHub Copilot.
PYAS: Python & C++ Antivirus with ML and Behavioral Monitoring
PYAS is an advanced antivirus software developed using a hybrid approach of Python and C++. It leverages machine learning and behavioral monitoring to effectively detect and block various threats. This project offers comprehensive security for Windows systems, combining user-mode scanning with kernel-mode protection.
mullvadvpn-app: Secure and Private Mullvad VPN Client for Desktop and Mobile
The `mullvadvpn-app` is the official open-source client application for the Mullvad VPN service, designed for both desktop and mobile platforms. Developed by Mullvad VPN AB, this project is primarily written in Rust, with frontends built using Electron for desktop and native implementations for Android and iOS. It provides a secure, privacy-preserving VPN experience, supporting protocols like WireGuard and OpenVPN, and is known for its strong emphasis on user anonymity and leak prevention.
GHunt: An Offensive Google Framework for OSINT and Data Collection
GHunt is a powerful Python-based offensive Google framework primarily focused on Open-Source Intelligence (OSINT), designed for efficient evolution. It offers robust CLI usage, Python library integration, and fully asynchronous operations, making it a versatile tool for gathering information related to Google services. With features like JSON export and a companion browser extension for streamlined login, GHunt simplifies the process of digital data collection.
Technitium DNS Server: Self-Host for Enhanced Privacy and Security
Technitium DNS Server is an open-source, cross-platform DNS server designed for self-hosting to improve privacy and security. It offers features like ad and malware blocking, encrypted DNS protocols (DoT, DoH, DoQ), and a user-friendly web console. This powerful tool provides network-wide control over DNS resolution, enhancing performance and offering detailed insights.
wush: Fast, Secure File Transfer and Shells over WireGuard
wush is a command-line tool designed for rapid and secure file transfers and shell access between computers. It leverages WireGuard for peer-to-peer connections, eliminating the need for trusted relay servers. This tool offers a robust and versatile solution for network communication.
OSV-Scanner: Comprehensive Vulnerability Scanning for Your Projects
OSV-Scanner is a powerful vulnerability scanner developed by Google, written in Go. It leverages the comprehensive OSV.dev database to identify security flaws across a wide range of project types, including various languages, package managers, and container images. The tool also provides advanced features like guided remediation, license scanning, and offline scanning capabilities.