Havuz

Constitutional governance runtime for autonomous AI agents

A privacy-first Android for Google Pixel phones: Tor-only encrypted chat (OMEMO + PGP), Tor Browser, a camera and an optional Monero wallet.

Black-box web penetration testing automation framework for AI Agents

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

Open-source, auditable application firewall and connection monitor for macOS.

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

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

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

Agentic code review with structural graph intelligence — PR gate + branch stewardship. Self-hosted. Apache-2.0.

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

Donate your spare AI usage for Open Source security

Open-source, self-hosted security pipeline for IT, AI and OT. Logs in. Evidence out.: OCSF normalization, 46 detection rules (MITRE/ATLAS/IC

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

Open-source, local-first desktop security suite for malware scanning, system audits, and maintenance.

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-first, self-hosted AI agents - isolation you can prove, not just promise.

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

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

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

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

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

Automated SSH and server provisioning installer for Linux environments with secure configuration, key management, system hardening, and depl

🔍 AI-powered automated code review tool that analyzes syntax, performance bottlenecks, and security flaws in pull requests.

Local-first password manager — zero cloud, zero telemetry. Rust+Tauri 2+XChaCha20-Poly1305+Argon2id+SQLCipher. 6 item types incl. Servers, B

Advanced Cloudflare DNS management extension for Plesk with DNS record synchronization, zone management, proxy control, SSL automation, and

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

Free security skills for AI-built apps — run /lictor-security-check in Claude Code before you ship. Plain English, read-only, no telemetry.

Terminal-native passive OSINT CLI for local-first public-source investigations, evidence correlation, and case management.

Open-source verifiable audit infrastructure. Built for lean, pre-series B, AWS-Native teams.

Published: 2026-10-18