AuditMeScan GitHub repos for production readiness in under 60 seconds

BugDaddy

BugDaddy is an AI-powered GUI debugger that scans projects, detects real bugs, and auto-fixes them from a desktop app. It supports 30+ languages, offers three scanning modes, and includes diff preview. Currently 100% free to download and in public beta.

Checkmarx Next-Gen SAST

Checkmarx Next-Gen SAST integrates three scanning layers into one engine: a battle-tested rules-based foundation, a purpose-tuned LLM covering any language including AI-generated code, and a new Finding Analysis Engine (FAE) that filters results to confirmed true positives — so developers see only what matters. Available now to all Checkmarx One customers as part of their existing subscription.

VibeMass

VibeMass scans an AI-generated codebase and returns a 0-100 Aura Health Score with plain-English business risk cards. A five-agent AI swarm reviews security, architecture, reliability, and performance, then hands you context-rich prompts to paste into Cursor, Windsurf, or Copilot for the fix.

CodeReview AI

CodeReview AI is a VS Code extension with a completely free, built-in AI — no API key or credit card needed. Select code, press Cmd+Alt+R, get instant bug detection, performance analysis, security scanning, and a quality score. One-click fixes and inline diagnostics.

ZenVeil

ZenVeil is a developer-focused security tool that reduces the complexity of traditional security tools. It scans GitHub repositories, local codebases, and APIs for secrets, supply chain risks, and common security issues. AI-powered explanations and remediation guidance help prioritize findings, and fixes can be delivered via pull requests. Accessible through a web dashboard or CLI.

GhostCheck

GhostCheck is a local, proof-based vulnerability scanner. Each finding includes proof of exploit to cut false positives, scans stay on your own network, and results export to PDF.

CyberStrikeAI: Turning Natural Language into Governed Multi-Agent Security Operations

CyberStrikeAI is an open-source platform written in Go that converts natural-language intent into governed multi-agent security operations, integrating over 100 tools and providing audit logs.

h4cker: A Massive Open-Source Security Learning Hub

h4cker is an expansive open-source project on GitHub, curated by Omar Santos. It compiles thousands of learning resources spanning ethical hacking, bug bounties, digital forensics, incident response, AI security, and reverse engineering. Primarily presented in Jupyter Notebooks, this repository has garnered nearly 30,000 stars, making it an invaluable guide for both security novices and seasoned professionals seeking structured learning paths.

pentagi: Multi-Agent Automated Penetration Testing System

pentagi is an open-source multi-agent system that automates penetration testing within Docker sandboxes, wrapping 20+ security tools with vector memory. The project is primarily written in Go and is licensed under the MIT license. As of the collection time, it has 21,587 stars on GitHub.

reverse-skill: Packaged Reverse Engineering and Pentesting Workflows for AI Agents

reverse-skill is an open-source project written in PowerShell, released under the MIT license. It packages 40+ reverse-engineering, pen-testing, and CTF workflows into a routing system designed for AI agents such as Claude Code, Cursor, and Cline. The project had 6574 GitHub stars at the time of collection.

awesome-ai-security: Curated Resources for AI Security

awesome-ai-security is a popular GitHub repository curating essential resources for AI security. It brings together papers, code, and tools covering adversarial examples, prompt injection, model privacy, and red-teaming. The project is licensed under MIT and had 1340 stars at the time of collection, making it a valuable reference for security researchers and AI developers.

kodus-ai: Open-Source AI Code Review with Model Control

kodus-ai is an open-source AI code review tool built with TypeScript, integrating various AI models like GPT and Claude. It empowers developers to choose their preferred models, avoid vendor lock-in, and enhance code review efficiency. With over 1200 stars on GitHub, it suits teams prioritizing autonomy and cost-effectiveness.