Project CodeGuard
Security framework for AI coding agents to prevent vulnerabilities
Visit project-codeguard.org ↗What is Project CodeGuard?
Project CodeGuard is an open-source framework designed to integrate security best practices directly into AI coding workflows. It provides rules and validators that guide AI assistants toward generating safer code by addressing common vulnerabilities like unvalidated input, hardcoded secrets, weak cryptography, and missing authentication checks.
The framework works across multiple stages—before, during, and after code generation—and supports popular coding agents through translators and plugins. Built by the Coalition for Secure AI (CoSAI), it helps teams embed security considerations throughout development rather than treating them as an afterthought, maintaining the speed benefits of AI coding tools while reducing risk.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered Project CodeGuard automatically. Evidence: GitHub cosai-oasis/project-codeguard; repo topic "ai-generated-code". View source.
Similar vibe-coded apps

Turn your codebase into a queryable knowledge graph for AI coding assistants

Operating layer for AI coding agents with skills, memory, planning and security

Self-hosted AI agent with persistent memory and multi-platform messaging

Open-source AI platform for short-form video and animated series creation


Open-source canvas workbench for AI-powered image and video creation

Community marketplace for DeepSeek Harness Web themes, pets, plugins

Open-source, AI-native knowledge base with Evernote-style interface