JoySafeter

The AI-native platform for building, orchestrating, and running security agents at scale.
_{From idea to production-grade security automation — in minutes, not months.}

English | 简体中文

Why JoySafeter

Traditional security tooling hits a ceiling: scripts are brittle, single agents lack context, and complex scenarios require 2–3 engineers working in parallel. JoySafeter breaks that ceiling.

JoySafeter defines a new paradigm: AI-driven Security Operations (AISecOps) — where multi-agent collaboration, cognitive memory, and scenario-matched skills replace manual coordination.

Real-World Cases

Case 1 — APK Vulnerability Detection Agent

Upload an APK. Get an OWASP Mobile Top 10 report. No engineer required.

How it works:

1. User uploads the APK file
2. Agent invokes MobSF for static analysis
3. Extracts critical risk signals — permission abuse, hardcoded secrets, insecure network config
4. Deep-validates high-severity findings via Frida dynamic instrumentation
5. Auto-generates a structured report aligned to OWASP Mobile Top 10

The entire flow — from upload to report — requires zero manual intervention, covering work that traditionally takes 2–3 security engineers.

Case 2 — Penetration Testing Agent

Describe the target and scope. The agent plans, executes, and adapts — then delivers a report.

How it works:

1. Open the Workbench and create a new agent
2. Enable DeepAgents mode → select penetration testing skills
3. Provide an authorized target URL and test requirements
4. Agent runs autonomously — if it discovers a login page, it automatically triggers auth bypass testing
5. Download the final report when the run completes

Note: Requires sandbox image swr.cn-north-4.myhuaweicloud.com/ddn-k8s/ghcr.io/jd-opensource/joysafeter-sandbox:latest configured in Sandbox Settings.

This dynamic decision-making — where the agent adapts its next step based on what it finds — is what fixed scripts cannot replicate.

Core Capabilities

Quick Start

One-Click Launch (Recommended)

./deploy/quick-start.sh

The script provides an interactive menu to choose your startup mode and customize ports (with conflict detection):

All modes support remote deployment scenarios:

• Docker Compose Full Stack — choose deployment address (localhost or IP/domain) + http/https
• Local Frontend Only — optionally connect to a remote backend API (enter backend IP + port + protocol)
• Local Backend Only — optionally connect to remote PostgreSQL, Redis, and frontend (enter each address and port)
• Local Frontend + Backend — optionally expose services via a non-localhost address
• Non-localhost deployments automatically update frontend/.env CSP whitelist (NEXT_PUBLIC_CSP_CONNECT_SRC_EXTRA)

./deploy/quick-start.sh --skip-env       # Skip .env file initialization
./deploy/quick-start.sh --skip-db-init   # Skip database initialization

Launch by Scenario

# ─── Development ────────────────────────────────────────
./deploy/scripts/dev.sh                  # Docker full-stack dev (containerized frontend + backend)
./deploy/scripts/dev-local.sh            # Local dev prep (start middleware, run backend/frontend on host)
./deploy/scripts/dev-backend.sh          # Local backend only (requires middleware running)
./deploy/scripts/dev-frontend.sh         # Local frontend only (requires backend running)

# ─── Production ─────────────────────────────────────────
./deploy/scripts/prod.sh                 # Production deploy (pre-built images + docker-compose.prod.yml)
./deploy/scripts/prod.sh --skip-mcp      # Production without MCP service
./deploy/scripts/prod.sh --skip-pull     # Skip image pull, use local images

# ─── Middleware / Infrastructure ────────────────────────
./deploy/scripts/start-middleware.sh     # Start middleware (PostgreSQL + Redis + MCP)
./deploy/scripts/minimal.sh             # Minimal startup (PostgreSQL + Redis only)
./deploy/scripts/minimal.sh --with-mcp  # Minimal + MCP service
./deploy/scripts/stop-middleware.sh      # Stop middleware

# ─── Test / CI ──────────────────────────────────────────
./deploy/scripts/test.sh                 # Test environment (minimal deps, automation-friendly)

# ─── Install / Check ───────────────────────────────────
./deploy/install.sh                      # Interactive installation wizard (generates config files)
./deploy/install.sh --mode dev --non-interactive  # Non-interactive install
./deploy/scripts/check-env.sh           # Environment preflight (Docker, ports, config files)

# ─── Image Management ──────────────────────────────────
./deploy/deploy.sh build                 # Build frontend + backend images
./deploy/deploy.sh build --all           # Build all images (including OpenClaw)
./deploy/deploy.sh push                  # Build and push to registry
./deploy/deploy.sh pull                  # Pull latest pre-built images

Default Ports

Prerequisites: Docker + Docker Compose. See INSTALL.md for detailed installation guide, deploy/PRODUCTION_IP_GUIDE.md for production deployment.

Architecture

Full architecture details: docs/ARCHITECTURE.md

Key design principles:

• Graph-based execution — every agent workflow is a stateful LangGraph, enabling pause, resume, and branch
• Unified Run Center — Chat, Copilot, and Skill Creator share a single event-sourced run lifecycle (Run → Event → Snapshot)
• Unified WebSocket layer — BaseWsClient abstract class; Chat / Run / Notification clients share lifecycle, auth (ws-token), and reconnect logic
• Full-chain trace_id propagation — contextvars-based request tracing from HTTP/WS entry through LangGraph to persistence
• Glass-box observability — real-time Langfuse tracing of every agent decision and state transition
• RAII sandbox isolation — per-user Docker containers with automatic handle release, zero state leakage
• Canonical model identifiers — full-stack (provider_name, model_name) resolution via ModelService → ModelFactory
• Layered skill system — skills are versioned units that compose into workflows without coupling

User Journey — Quick Start in 9 Steps

Login → Configure Models → MCP Tools → Skill Management → Build Agent → Self-Test (Langfuse Trace) → Publish → Chat UI → Run Center

Tech Stack

What's New

Full history: CHANGELOG.md

Documentation

Getting Started

• INSTALL.md — Installation guide (Docker / manual / pre-built images)
• DEVELOPMENT.md — Local development setup
• deploy/README.md — Docker deployment
• deploy/PRODUCTION_IP_GUIDE.md — Production deployment

Deep Dive

• docs/ARCHITECTURE.md — Architecture overview
• backend/README.md — Backend guide
• frontend/README.md — Frontend guide

Tutorials

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

Governance

• CONTRIBUTING.md — Contributing guide
• SECURITY.md — Security policy
• CODE_OF_CONDUCT.md — Code of conduct

Community

Join the WeChat user group for questions and discussion:

Contributing

git clone https://github.com/jd-opensource/JoySafeter.git
git checkout -b feature/amazing-feature
git commit -m 'feat: add amazing feature'
git push origin feature/amazing-feature

See CONTRIBUTING.md for full guidelines.

License

Apache License 2.0 — see LICENSE for details.

Third-party component licenses: THIRD_PARTY_LICENSES.md

Acknowledgments

LangChain

LangGraph

FastAPI

Next.js

Radix UI

_{Made with ❤️ by the JoySafeter Team
For commercial solutions, contact JD Technology Solutions Team at [email protected]}