Skip to content

pwddd/JoySafeter

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

399 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

JoySafeter

Visual platform for building, orchestrating, and running AI security agents — from idea to production in minutes.

License: Apache 2.0 Python 3.12+ Node.js 20+ LangGraph FastAPI MCP Protocol

English | 简体中文


Quick Start

Get JoySafeter running in one command:

./deploy/quick-start.sh
Service URL
Frontend http://localhost:3000
Backend API http://localhost:8000
API Docs http://localhost:8000/docs

Prerequisites: Docker + Docker Compose. See INSTALL.md for manual setup or pre-built images.


What's New

Full history: CHANGELOG.md

Tag Feature What it means
NEW Skill Versioning & Collaboration Publish, rollback, and manage skill versions; invite collaborators with role-based permissions; platform API tokens for CI/CD integration
NEW Multi-Tenant Sandbox Engine Per-user isolated code execution — no state leakage between sessions
NEW Enterprise SSO Built-in GitHub / Google / Microsoft templates, plus OIDC (Keycloak, Authentik, GitLab) and JD SSO
UPGRADE DeepAgents v0.4 Latest stability improvements and performance optimizations for the multi-agent kernel
UPGRADE Glass-Box Observability Real-time Langfuse tracing of every agent decision and state transition

Key Features

Build Agents Visually

  • No-code workflow builder — drag-and-drop nodes with loops, conditionals, and parallel execution
  • Rapid Mode — describe what you need in natural language, get a running agent team in minutes
  • Deep Mode — fine-tune workflows with visual debugging and step-by-step observability

200+ Security Tools Built In

  • Pre-integrated Nmap, Nuclei, Trivy, and more
  • MCP Protocol — extend with any tool via Model Context Protocol
  • 30+ pre-built skills — penetration testing, document analysis, cloud security, and more

Enterprise Ready

  • Multi-tenancy — isolated workspaces with role-based access
  • Full audit trail — execution tracing and governance
  • SSO integration — GitHub, Google, Microsoft, OIDC, JD SSO
  • Production deployment — Docker Compose with one-click scripts

AI-Native Architecture

  • DeepAgents — manager-worker multi-level agent orchestration
  • Memory evolution — long/short-term memory for continuous learning
  • Skill system — versioned, reusable capability units with progressive disclosure
  • LangGraph engine — graph-based workflows with full state management

Architecture

Detailed architecture: docs/ARCHITECTURE.md

JoySafeter Architecture


Tech Stack

Layer Technology Purpose
Frontend Next.js 16, React 19, TypeScript Server-side rendering, App Router
UI Radix UI, Tailwind CSS, Framer Motion Accessible, animated components
State Zustand, TanStack Query Client & server state
Workflow Editor React Flow Interactive node-based builder
Backend FastAPI, Python 3.12+ Async API with OpenAPI docs
AI Framework LangChain, LangGraph, DeepAgents Agent orchestration & workflows
MCP mcp 1.20+, fastmcp 2.14+ Tool protocol support
Database PostgreSQL, SQLAlchemy 2.0 Async ORM with migrations
Cache Redis Session cache & rate limiting
Observability Langfuse, Loguru Tracing & structured logging

Documentation

Getting Started

Deep Dive

Tutorials

See docs/tutorials/ for step-by-step guides on model setup, MCP integration, skill development, and more.

Governance


Roadmap

See docs/plans/ and project issues for the latest roadmap and design notes.


Community

Join the WeChat user group if you have questions or want to connect with other users:

JoySafeter User Group

Contributing

We welcome contributions! See CONTRIBUTING.md for details.

# Fork and clone
git clone https://github.com/jd-opensource/JoySafeter.git

# Create feature branch
git checkout -b feature/amazing-feature

# Make changes and commit
git commit -m 'feat: add amazing feature'

# Push and create PR
git push origin feature/amazing-feature

License

This project is licensed under the Apache License 2.0 — see the LICENSE file for details.

Note: This project includes third-party components with different licenses. See THIRD_PARTY_LICENSES.md for details.


Acknowledgments


LangChain

LangGraph

FastAPI

Next.js

Radix UI

Made with ❤️ by the JoySafeter Team

For commercial solutions, please contact JD Technology Solutions Team at org.ospo1@jd.com

About

please add desp

Resources

License

Code of conduct

Contributing

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • Python 54.4%
  • TypeScript 42.3%
  • Shell 2.0%
  • JavaScript 0.7%
  • Dockerfile 0.4%
  • CSS 0.1%
  • Other 0.1%