Havuz

LordOS — a free, fast and secure GNU/Linux distribution based on Debian, with its own desktop environment: display server and Wayland compos

An AI that administers Linux through typed, approval-gated, Ed25519-audited actions. The model selects the action; the daemon builds the com

AVault - Call Recorder (No Root Required) | Privacy-first, hardware-encrypted audio vault for Android 12-16+. Rootless call recording via Sh

Autonomous AI pentesting agents — real-time reconnaissance, vulnerability detection, and exploitation orchestration. Go + TypeScript.

World's first Face Authentication enabled MacOS App-locker, completely free and open-source. Unlock your Mac apps using Face , TouchID or pa

Open-Source alternative app store for Android aimed to provide a secure Google Play alternative, offering verified, open-source apps with bu

Niubi Guard, GitHub repository’lerindeki Issue ve yorumları spam, taciz ve koordineli abuse açısından tarayıp yapılandırılabilir yanıtlar öneren bir CLI ve web arayüzüdür.

Neden yükseliyor · 1310 yıldızın 116 günde toplanması ve README’deki Trendshift görünürlüğü dikkat çektiğini gösteriyor; ancak bunun hangi kullanıcı ihtiyacından kaynaklandığı veya gerçek kullanım düzeyi ölçümlerden doğrulanamıyor. Son 28 günde commit ve farklı yazar yok; bu nedenle ilginin güncel geliştirme ya da benimsemeyle sürdüğüne dair kanıt bulunmuyor.

Cover your Mac's screen with a hotkey while AI agents keep running, even with the lid closed. The covered screen glows when Claude Code, Cod

Agent-assisted maintainership and development framework for Apache projects — Triage, Mentoring, Drafting (agent-authored fixes with human r

Universal Zero-Refusal Agent Framework - 40+ jailbreak templates (T1-T119), 1128 curated skills, executable framework-core, installer untuk

Catch dangerous AI agent skills before they catch you. Zero-dependency security scanner for Agent Skills, SKILL.md and MCP configs.

OpenLock — a free, open-source App Lock for Android. Lock any app behind a PIN, pattern, or fingerprint, with Device-Admin uninstall protect

Store, share, and resume AI coding sessions.

Personal AI assistant for work inside corporate constraints, built on coding agents and the tools, sessions, and permissions you already hav

Open-source cybersecurity analysis agent for Claude Code. Scans projects for vulnerabilities across all OWASP 2025 Top 10 and CWE Top 25 cat

Dependency-free preflight checks for repositories before making them public

Automated detection and tracking of fake engagement on GitHub — daily CI, zero infrastructure

Lightweight open-core SIEM in Rust — S3-compatible for logs, Postgres for state.

Open-source AI-powered website audit CLI using the OpenAI API for SEO, UX, accessibility, performance, trust, and content analysis.

Agent skill for producing threat models for open-source projects

Hardening Linux automatisé avec Ansible — conformité ANSSI BP-028 (niveaux M/I/R/E). Durcissement système, réseau, SSH, utilisateurs + audit

Open-source security gateway & static scanner for AI agents. Enforce role-based access control (RBAC), human-in-the-loop approvals, segreg

Open-source security audits for Supabase: a read-only MCP server, a CLI agent and a Claude Skill. Finds RLS misconfigurations, exposed keys

Encrypts folders and files on Linux Mint (Cinnamon/Nemo) using AES-256, making it feel like a native part of the system: double-click on the

C2 server fingerprinter — Cobalt Strike, Sliver, Mythic, Havoc, Brute Ratel

Modular post-install setup script for Fedora Linux (KDE)

Evidence-driven production readiness checklist for shipping web applications with confidence

Cryptographic trust and authorization evidence for AI agents. Every action a receipt, every grant a proof.

Automatic, model-driven permission review for OpenCode

DropLink is a decentralized, temporary peer-to-peer sharing platform. Files, folders, links, and chat messages move directly between browser

Privacy-first SOS application for sending emergency messages and real-time location updates to trusted contacts.

Black-box web penetration testing automation framework for AI Agents

OSS license watchdog. Monitors GitHub repos you depend on and alerts you when a license changes, explaining exactly what you can no longer d

Security gate for AI-generated code - blocks the build until vulnerabilities are fixed

Donate your spare AI usage for Open Source security

A secure, production-ready Python CLI wrapper for Nmap that makes powerful scans easy and repeatable. Includes 12 built-in profiles (SYN, ag

AI Agent 的安全守门员。在API 返回结果用户确认执行之前，及时拦截危险内容。The safety gatekeeper for AI Agents. Timely intercept dangerous content before the API returns re

Open-source AI security tool to scan and fix vulnerabilities in your vibe-coded projects before you ship. AXguard by AwareXone.

CryptoSafe | AES-256-GCM + Argon2 ID — Encrypt text securely, completely offline. No internet. No tracking. Open source.

easybackend.js is a developer-friendly backend DSL and framework for building Node.js/Express APIs with validation, auth, database, and secu

Open-source macOS security app with local Endpoint Security monitoring, YARA scanning, behavioral detection, Email Guard, and network filter

Bounded repository context and verified patches for Codex and Claude Code. Explicit edit grants, source fingerprints, isolated worktrees, ac

Claude and ChatGPT now log into your app as your customers. OneHuman decides what they can see and do. Join our community: https://discord.g

Open-source Supabase security auditor: detects RLS-disabled tables, public buckets, exposed SECURITY DEFINER functions. Active anonymous pro

High-performance Rust-based DNS-over-TLS (DoT) server with advanced ad-blocking for Android via Termux.

🐾 PAW Agents — The operating system for autonomous AI workers. Safe, extensible, traceable AI execution for Solana and beyond.

Think first, then code. Where Claude Code and Codex jump straight to writing, this stays review-first: a code reviewer, security scanner, ro

Security guidance based on library and version for developers and agents.

Passive blue-team security scanner — 582 read-only modules, plus 32 opt-in probes. Runs on your machine. No accounts. No telemetry.

Local-first password, 2FA and recovery vault for Windows and Linux. Your vault is encrypted on your device and never sent to a server. AGPL.