# AgentScope Samples
[](https://github.com/agentscope-ai/agentscope-samples/blob/main/LICENSE)
[](https://www.python.org/)
[](https://deepwiki.com/agentscope-ai/agentscope-samples)
[](https://doc.agentscope.io/)
[](https://runtime.agentscope.io/)
[](https://github.com/agentscope-ai/agentscope-samples)
[[δΈζREADME]](README_zh.md)
π― **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**.
## π What is AgentScope?
**[AgentScope](https://github.com/agentscope-ai/agentscope)** is a **multi-agent framework** that lets you rapidly build **LLM-based intelligent applications**:
> Learn more in the [AgentScope Documentation](https://doc.agentscope.io/)
- π§ Define agents and integrate tools
- π‘ Manage context and conversations
- π€ Orchestrate collaboration among multiple agents to accomplish tasks
**[AgentScope-Runtime](https://github.com/agentscope-ai/agentscope-runtime)** is the runtime framework that enables you to deploy agents as API services:
> Learn more in the [AgentScope Runtime Documentation](https://runtime.agentscope.io/)
1. π **Scalable deployment management for multiple agents**
2. π‘οΈ **Secure sandbox execution for tools**
## β‘ Getting Started
π **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`**.
## π³ Repository Structure
```bash
βββ alias/ # Agent to solve real-world problems
βββ browser_use/
β βββ agent_browser/ # Pure Python browser agent
β βββ browser_use_agent_pro/ # Advanced pure python browser agent
β βββ browser_use_fullstack_runtime/ # Full-stack runtime version with frontend/backend
β
βββ deep_research/
β βββ agent_deep_research/ # Pure Python multi-agent research
β βββ qwen_langgraph_search_fullstack_runtime/ # Full-stack runtime-enabled research app
β
βββ games/
β βββ game_werewolves/ # Role-based social deduction game
β
βββ conversational_agents/
β βββ chatbot/ # Chatbot application
β βββ chatbot_fullstack_runtime/ # Runtime-powered chatbot with UI
β βββ multiagent_conversation/ # Multi-agent dialogue scenario
β βββ multiagent_debate/ # Agents engaging in debates
β
βββ evaluation/
β βββ ace_bench/ # Benchmarks and evaluation tools
β
βββ data_juicer_agent/ # Data processing multi-agent system
βββ sample_template/ # Template for new sample contributions
βββ README.md
```
## π Example List
| Category | Example Folder | Uses AgentScope | Use AgentScope Runtime | Description |
| ----------------------- |-------------------------------------------------------| --------------- | ------------ |--------------------------------------------------|
| **Data Processing** | data_juicer_agent/ | β
| β | Multi-agent data processing with Data-Juicer |
| **Browser Use** | browser_use/agent_browser | β
| β | Command-line browser automation using AgentScope |
| | browser_use/browser_use_agent_pro | β
| β | Advanced command-line Python browser agent using AgentScope |
| | browser_use/browser_use_fullstack_runtime | β
| β
| Full-stack browser automation with UI & sandbox |
| **Deep Research** | deep_research/agent_deep_research | β
| β | Multi-agent research pipeline |
| | deep_research/qwen_langgraph_search_fullstack_runtime | β | β
| Full-stack deep research app |
| **Games** | games/game_werewolves | β
| β | Multi-agent roleplay game |
| **Conversational Apps** | conversational_agents/chatbot_fullstack_runtime | β
| β
| Chatbot application with frontend/backend |
| | conversational_agents/chatbot | β
| β | |
| | conversational_agents/multiagent_conversation | β
| β | Multi-agent dialogue scenario |
| | conversational_agents/multiagent_debate | β
| β | Agents engaging in debates |
| **Evaluation** | evaluation/ace_bench | β
| β | Benchmarks with ACE Bench |
| **General AI Agent** | alias/ | β
| β
| Agent application running in sandbox to solve diverse real-world problems |
| **Financial Trading** | evotraders/ | β
| β | Self-Evolving Multi-Agent Trading System |
## π Featured Examples
### π 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
π **Documentation**: [English](data_juicer_agent/README.md) | [δΈζ](data_juicer_agent/README_ZH.md)
### π΅π» 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.
π **Documentation**: [English](alias/README.md) | [δΈζ](alias/README_ZH.md)
### π 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.
π **Documentation**: [English](evotraders/README.md) | [δΈζ](evotraders/README_zh.md)
## π Getting Help
If you:
- Need installation help
- Encounter issues
- Want to understand how a sample works
Please:
1. Read the sample-specific `README.md`.
2. File a [GitHub Issue](https://github.com/agentscope-ai/agentscope-samples/issues).
3. Join the community discussions:
| [Discord](https://discord.gg/eYMpfnkG8h) | DingTalk |
| ------------------------------------------------------------ | ------------------------------------------------------------ |
|
|
|
## π€ Contributing
We welcome contributions such as:
- Bug reports
- New feature requests
- Documentation improvements
- Code contributions
See the [CONTRIBUTING.md](CONTRIBUTING.md) for details.
## π License
This project is licensed under the **Apache 2.0 License** β see the [LICENSE](LICENSE) file for details.
## Contributors β¨
[](#contributors-)
Thanks goes to these wonderful people ([emoji key](https://allcontributors.org/emoji-key/)):