How to Deploy JoyAgent AI Agent on JD Cloud in Four Simple Steps
This guide walks you through deploying JD Cloud’s open‑source JoyAgent AI agent using the JoyAgent‑Genie image, covering host creation, firewall configuration, model and search engine setup, and service startup, enabling you to access the Genie interface via a public IP.
JD Cloud recently open‑sourced JoyAgent, the first fully open‑source enterprise‑grade AI agent, providing front‑end, back‑end, framework, engine and core sub‑agents. To simplify deployment, JD Cloud offers a ready‑made JoyAgent‑Genie image. The following guide shows how to deploy it.
Step 1: Create a lightweight cloud host
Choose the JoyAgent‑Genie image, set the package version and duration, and order a lightweight cloud host instance.
Step 2: Open ports and obtain public IP
After payment, view the purchased host in the console, note the IP address, and click “View”. In the firewall tab, add rules to open ports 1601, 3000 and 8080.
Step 3: Configure model and search engine
Using DeepSeek as the LLM and Serper as the search engine, edit the configuration files on the host:
In genie-backend/src/main/resources/application.yml, set the default model to deepseek-chat.
In genie-tool/.env, set the model API key, SERVER_IP (the public IP noted earlier), and the search engine API key.
In ui/src/utils/querySSE.ts and ui/vite.config.ts, prepend http:// to the public IP.
Step 4: Start the service
Run ./Genie_start.sh until the log shows the service is ready. Then open a browser and navigate to http://{public_ip}:3000 to access the Genie UI (initial load may be slow).
JD Tech Talk
Official JD Tech public account delivering best practices and technology innovation.
How this landed with the community
Was this worth your time?
0 Comments
Thoughtful readers leave field notes, pushback, and hard-won operational detail here.