AgentScope Samples

[中文README]

🎯 Kickstart Your Agent Journey! This is a repository that brings together a variety of ready-to-run Python agent examples, ranging from command-line mini-tools to full-stack deployable applications.

🌟 What is AgentScope?

AgentScope is a multi-agent framework that lets you rapidly build LLM-based intelligent applications:

Learn more in the AgentScope Documentation

🧠 Define agents and integrate tools
📡 Manage context and conversations
🤝 Orchestrate collaboration among multiple agents to accomplish tasks

AgentScope-Runtime is the runtime framework that enables you to deploy agents as API services:

Learn more in the AgentScope Runtime Documentation

🔄 Scalable deployment management for multiple agents
🛡️ Secure sandbox execution for tools

⚡ Getting Started

📌 Before running an example, please check the corresponding README.md for installation and execution instructions.

All examples are built with Python.

Examples are organized by functionality and usage scenario.

Some examples use AgentScope only.

Some examples use both AgentScope and AgentScope Runtime to implement deployable full-stack applications with frontend + backend.

Full-stack runtime versions have folder names ending with _fullstack_runtime.

🌳 Repository Structure

├── alias/                                  # Agent to solve real-world problems
├── browser_use/
│   ├── agent_browser/                      # Pure Python browser agent
│   ├── browser_use_agent_pro/              # Advanced pure python browser agent
│   └── browser_use_fullstack_runtime/      # Full-stack runtime version with frontend/backend
│
├── deep_research/
│   ├── agent_deep_research/                # Pure Python multi-agent research
│   └── qwen_langgraph_search_fullstack_runtime/    # Full-stack runtime-enabled research app
│
├── games/
│   └── game_werewolves/                    # Role-based social deduction game
│
├── conversational_agents/
│   ├── chatbot/                            # Chatbot application
│   ├── chatbot_fullstack_runtime/          # Runtime-powered chatbot with UI
│   ├── multiagent_conversation/            # Multi-agent dialogue scenario
│   └── multiagent_debate/                  # Agents engaging in debates
│
├── evaluation/
│   └── ace_bench/                          # Benchmarks and evaluation tools
│
├── data_juicer_agent/                      # Data processing multi-agent system
├── tuner/                                  # Tune AgentScope applications using AgentScope Tuner
│   ├── math_agent/                         # A quick start example for tuning
│   ├── frozen_lake/                        # Teach an agent to play a game requiring multiple steps
│   ├── learn_to_ask/                       # Using LLM-as-a-judge to facilitate agent tuning
│   ├── email_search/                       # Enhance the tool use ability of your agent
│   ├── werewolves/                         # Enhance a multi-agent application
│   └── data_augment/                       # Data augmentation for tuning
├── sample_template/                        # Template for new sample contributions
└── README.md

📌 Example List

Category	Example Folder	Uses AgentScope	Use AgentScope Runtime	Description
Data Processing	data_juicer_agent/	✅	❌	Multi-agent data processing with Data-Juicer
Browser Use	browser_use/agent_browser	✅	❌	Command-line browser automation using AgentScope
	browser_use/browser_use_agent_pro	✅	❌	Advanced command-line Python browser agent using AgentScope
	browser_use/browser_use_fullstack_runtime	✅	✅	Full-stack browser automation with UI & sandbox
Deep Research	deep_research/agent_deep_research	✅	❌	Multi-agent research pipeline
	deep_research/qwen_langgraph_search_fullstack_runtime	❌	✅	Full-stack deep research app
Games	games/game_werewolves	✅	❌	Multi-agent roleplay game
Conversational Apps	conversational_agents/chatbot_fullstack_runtime	✅	✅	Chatbot application with frontend/backend
	conversational_agents/chatbot	✅	❌
	conversational_agents/multiagent_conversation	✅	❌	Multi-agent dialogue scenario
	conversational_agents/multiagent_debate	✅	❌	Agents engaging in debates
Evaluation	evaluation/ace_bench	✅	❌	Benchmarks with ACE Bench
General AI Agent	alias/	✅	✅	Agent application running in sandbox to solve diverse real-world problems
Financial Trading	evotraders/	✅	❌	Self-Evolving Multi-Agent Trading System

🌈 Featured Examples

📊 DataJuicer Agent

A powerful multi-agent data processing system that leverages Data-Juicer's 200+ operators for intelligent data processing:

Intelligent Query: Find suitable operators from 200+ data processing operators
Automated Pipeline: Generate Data-Juicer YAML configurations from natural language
Custom Development: Create domain-specific operators with AI assistance
Multiple Retrieval Modes: LLM-based and vector-based operator matching
MCP Integration: Native Model Context Protocol support

📖 Documentation: English | 中文

🕵🏻 Alias-Agent

Alias-Agent (short for Alias) is designed to serve as an intelligent assistant for tackle diverse and complicated real-world tasks, providing three operational modes for flexible task execution:

Simple React: Employs vanilla reasoning-acting loops to iteratively solve problems and execute tool calls.
Planner-Worker: Uses intelligent planning to decompose complex tasks into manageable subtasks, with dedicated worker agents handling each subtask independently.
Built-in Agents: Leverages specialized agents tailored for specific domains, including Deep Research Agent for comprehensive analysis and Browser-use Agent for web-based interactions.

Beyond being a ready-to-use agent, we envision Alias as a foundational template that can be adapted to different scenarios.

📖 Documentation: English | 中文

📈 EvoTraders

EvoTraders is a financial trading agent framework that builds a trading system capable of continuous learning and evolution in real markets through multi-agent collaboration and memory systems. Key features include:

Multi-Agent Collaboration: A team of specialized analysts (Fundamentals, Technical, Sentiment, Valuation) and managers collaborating like a real trading team.
Memory Enhancement & Evolution: Agents reflect and summarize after trades using the ReMe memory framework, evolving their trading styles over time.
Real-Time & Backtesting: Supports both real-time market data integration for live trading and backtesting modes.
Visualized Dashboard: A comprehensive frontend to observe analysis processes, communication, and performance tracking.

📖 Documentation: English | 中文

🆘 Getting Help

If you:

Need installation help
Encounter issues
Want to understand how a sample works

Please:

Read the sample-specific README.md.
File a GitHub Issue.
Join the community discussions:

Discord	DingTalk

🤝 Contributing

We welcome contributions such as:

Bug reports
New feature requests
Documentation improvements
Code contributions

See the CONTRIBUTING.md for details.

📄 License

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

Contributors ✨

Thanks goes to these wonderful people (emoji key):

_{Weirui Kuang} 🚧 💻 👀 📖	_Osier-Yi 🚧 💻 👀 📖	_DavdGao 🚧	_qbc 🚧	_{Lamont Huffman} 💻 ⚠️	_{Daoyuan Chen} 💻 💡	_{MeiXin Chen} 💻 💡
_{Yilun Huang} 💻 💡	_ShenQianli 💻 💡	_ZiTao-Li 💻 💡	_{Yuexiang XIE} 💻 💡	_{Yue Cui} 💻 💡 🚧 📖	_{Zexi Li} 💻 💡	_lalaliat 💻 💡
_{Dandan Liu} 💻 💡	_{Tianjing Zeng} 💻 💡	_zhijianma 💻 💡	_Jiaji 💻 💡	_duoyw 💻 💡	_JustinDing 💻 💡	_jinliyl 💻 💡
_y1y5 💻 💡	_LuYi 💻 💡	_{Wu Yue} 💻 💡	_{Zhiling (Bruce) Luo} 💻 💡 📖	_sidiluo 💻	_Attan 💡 💻 📖
Add your contributions