ai-agent

AgentScope Java: Build LLM Apps

Name: AgentScope Java: Build LLM Apps
Author: agentscope-ai

Founders use AgentScope Java for agent-oriented programming, ideal for building AI applications with Java.

From the repo · “Build distributed, production-grade, long-running agents.”

6,079 stars+95★ this week1,524 forksJavaGuide quality 8/10 · reviewed Jul 9Updated 10/22/2026100% free · open source

What it does

AgentScope Java enables founders to build AI applications using agent-oriented programming in Java, allowing for the creation of autonomous agents that interact and cooperate to achieve complex tasks.

When to use it

•Building a multi-agent system that requires autonomous decision-making
•Developing an AI application that needs to adapt to changing environments
•Creating a simulation that involves interacting agents with distinct goals and behaviors

Ready-to-paste prompt

Run the `AgentScopeExample.java` file with the command `java -cp target/agentscope-java-1.0.0.jar com.agentscope.example.AgentScopeExample` to see a simple example of agent-oriented programming in action

Heads up: Ensure you have Java 11 or later installed, as AgentScope Java requires at least this version to function correctly, and verify that the `JAVA_HOME` environment variable is properly set

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/agentscope-java && curl -fsSL https://workflowstacks.com/api/skills/agentscope-java/claude-skill -o ~/.claude/skills/agentscope-java/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How AgentScope Java: Build LLM Apps works

Codeflow

Free to inspect

AgentScope Java: Build LLM Apps is a very large Java project (~535k lines across 2961 code files, plus 921 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size

Very large codebase

~535k lines · 2961 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Java/JVM

No API keys detected

Java 74%Go 15%TypeScript 9%Python 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
SKILL.md
The instructions the AI actually follows

What's in each folder

docs/Documentation467 files

agentscope-service/Folder1390 files

agentscope-extensions/Folder1341 files

agentscope-examples/Folder586 files

agentscope-core/Folder524 files

agentscope-harness/Folder416 files

agentscope-distribution/Folder3 files

agentscope-dependencies-bom/Folder1 files

READMEHas testsDocumentedCI checksApache-2.0 licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/agentscope-java && curl -fsSL https://workflowstacks.com/api/skills/agentscope-java/claude-skill -o ~/.claude/skills/agentscope-java/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

agentscope-ai

Language

Java