hackerai-tech/hackerai

Find and fix vulnerabilities by chatting with AI

What it solves

HackerAI is an AI-powered assistant designed to help users perform penetration testing. It automates and assists in the process of identifying and exploiting vulnerabilities in systems, acting as a specialized tool for security researchers and ethical hackers.

How it works

The system integrates several cloud services to function as an autonomous agent. It uses OpenRouter for AI model access, OpenAI for content moderation, and E2B for isolated cloud execution of code. Backend operations are managed by Convex (database) and Trigger.dev (durable runtime for agent tasks), while WorkOS handles authentication.

Who it’s for

Security researchers, penetration testers, and ethical hackers who want an AI-driven assistant to streamline their security auditing process.

Highlights

  • Isolated Execution: Uses E2B to run code in secure, isolated cloud sandboxes.
  • Agentic Workflow: Leverages Trigger.dev to maintain a durable runtime for long-running agent tasks.
  • ** uma Web Search**: Optional integration with Perplexity and Jina AI for retrieving real-time web content.
  • Comprehensive Infrastructure: Integrates a full stack of tools for authentication, database management, and payment processing.

Related

  • Project
    vxcontrol/pentagi

    An autonomous AI-powered penetration testing platform that uses a multi-agent system to automate security vulnerability research and exploitation in isolated environments.

  • Project
    cdxiaodong/cain-agent

    An AI-powered penetration testing engineer for authorized security assessments that automates the discovery of business-logic flaws and cloud misconfigurations across global and Chinese cloud providers.

  • Project
    yashab-cyber/HackGpt

    An AI-powered penetration testing platform for enterprise security teams that automates vulnerability assessments and compliance mapping using a multi-provider AI engine.

  • Project
    pensarai/apex

    An AI-powered penetration testing tool that uses autonomous agents to perform blackbox and whitebox security audits directly from the terminal.

  • Project
    ASCIT31/Dark-Moon

    DarkMoon is an open‑source, self‑hosted platform that uses a fleet of AI agents to run fully automated penetration tests. It orchestrates 50+ real offensive tools via a secure “MCP” gatekeeper, masks all sensitive data before it reaches the language model, and returns reproducible proof for every vulnerability. Supports web, cloud, AD, Kubernetes, databases, IoT and AI/LLM endpoints, runs on local LLMs for privacy, and is GPL‑3.0 licensed.