agentscope
Build and run agents you can see, understand and trust.
claude mcp add --transport stdio agentscope-ai-agentscope uvx agentscope
How to use
AgentScope is a powerful agent framework designed to facilitate the creation and deployment of intelligent agents. Users can quickly build agents using the built-in ReAct agent, which supports various functionalities such as tools, skills, human-in-the-loop steering, memory management, and real-time voice capabilities. The framework allows for flexible multi-agent orchestration and workflows, making it suitable for both simple and complex applications. To get started, users can follow the provided examples and tutorials that demonstrate how to implement different types of agents and workflows effectively.
How to install
To install AgentScope, ensure you have Python 3.10 or higher installed on your system. You can install the package directly from PyPI using the following command:
pip install agentscope
Alternatively, if you prefer to use the uv tool, you can run:
uv pip install agentscope
If you want to install from the source, clone the repository and install it in editable mode:
git clone -b main https://github.com/agentscope-ai/agentscope.git
cd agentscope
pip install -e .
Additional notes
When using AgentScope, ensure that your environment is properly configured for Python 3.10 or higher. Common issues may include dependency conflicts or installation errors, which can often be resolved by creating a virtual environment. Additionally, users can explore the extensive documentation and community resources available on Discord for support and collaboration. Environment variables may be required for certain functionalities, so refer to the documentation for specific configuration options.
Related MCP Servers
AstrBot
Agentic IM Chatbot infrastructure that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
PPTAgent
An Agentic Framework for Reflective PowerPoint Generation
open-ptc-agent
An open source implementation of code execution with MCP (Programatic Tool Calling)
llm-search
Querying local documents, powered by LLM
FireRed-OpenStoryline
FireRed-OpenStoryline is an AI video editing agent that transforms manual editing into intention-driven directing through natural language interaction, LLM-powered planning, and precise tool orchestration. It facilitates transparent, human-in-the-loop creation with reusable Style Skills for consistent, professional storytelling.
prism-insight
AI-based stock analysis and trading system