jd-opensource/JoySafeter

🚀 JoySafeter: An enterprise AI Agent Platform—Not just chatting. building、running、testing, and tracing autonomous Agent Teams with visual orchestration...

What it solves

JoySafeter addresses the limitations of traditional security tooling, where scripts are often brittle and manual coordination between engineers is required for complex tasks. It replaces manual security operations with AI-driven Security Operations (AISecOps), enabling the automation of high-effort tasks like APK vulnerability analysis and penetration testing through autonomous, adaptive agents.

How it works

The platform uses a multi-agent orchestration system powered by LangGraph and DeepAgents. It allows users to build security agents using a no-code visual editor or natural language descriptions. These agents can access over 200 pre-integrated security tools (such as Nmap, Nuclei, and Trivy) via the Model Context Protocol (MCP). The system employs a manager-worker collaboration model with long- and short-term memory to allow agents to adapt their actions based on real-time findings—for example, automatically triggering authentication bypass tests upon discovering a login page.

Who it’s for

It is designed for security engineers and organizations looking to scale their security automation, move from static playbooks to dynamic AI agents, and implement production-grade security orchestration with enterprise features like multi-tenancy and isolated sandboxes.

Highlights

  • Visual Agent Builder: A no-code drag-and-drop editor for creating complex workflows with loops and conditionals.
  • Extensive Tooling: Integration with 200+ security tools via MCP and 30+ pre-built skills.
  • DeepAgents Orchestration: Multi-level agent collaboration with evolving memory and state management.
  • Enterprise-Grade Infrastructure: Includes multi-tenant isolated sandboxes for secure code execution, SSO integration, and full audit trails.
  • Observability: Real-time tracing of agent decisions and state transitions via Langfuse.

Related

  • Project
    Kritt-ai/open-kritt

    An open-source security research platform that orchestrates AI agents to find, validate, and rank vulnerabilities in code through focused, parallelized workflows.

  • Project
    GH05TCREW/pentestagent

    An AI-powered penetration testing framework that automates security assessments using autonomous agents, multi-agent orchestration, and MCP-integrated security tools.

  • Project
    SHAdd0WTAka/Zen-Ai-Pentest

    An autonomous, AI-driven penetration testing framework that orchestrates over 72 security tools to automate reconnaissance, exploitation, and reporting.

  • 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
    aliasrobotics/cai

    An open-source framework for building AI-powered offensive and defensive security automation, used to establish the Cybersecurity AI research domain.