{"type":"mcp_client","name":"agentscope","description":"AgentScope is a framework designed to simplify the creation of LLM-powered multi-agent applications. It offers tools, documentation, and a drag-and-drop workstation for building and deploying agent-based systems. AgentScope is a","category":"AI","language":"Python","stars":26830,"forks":394,"owner":"modelscope","github_url":"https://github.com/modelscope/agentscope","homepage":"https://doc.agentscope.io/","setup":"## Setup\nAgentScope requires **Python 3.9** or higher.\n\n***Note: This project is currently in active development, it's recommended to\ninstall AgentScope from source.***\n\n### From source\n\n- Install AgentScope in editable mode:\n\n```bash\n# Pull the source code from GitHub\ngit clone https://github.com/modelscope/agentscope.git\n\n# Install the package in editable mode\ncd agentscope\npip install -e .\n```\n\n### Using pip\n\n- Install AgentScope from pip:\n\n```bash\npip install agentscope\n```\n\n### Extra Dependencies\n\nTo support different deployment scenarios, AgentScope provides several\noptional dependencies. Full list of optional dependencies refers to\n[tutorial](https://doc.agentscope.io/build_tutorial/quickstart.html)\nTaking distribution mode as an example, you can install its dependencies\nas follows:\n\n#### On Windows\n\n```bash\n# From source\npip install -e .[distribute]\n# From pypi\npip install agentscope[distribute]\n```\n\n#### On Mac & Linux\n\n```bash\n# From source\npip install -e .\\\\[distribute\\\\]\n# From pypi\npip install agentscope\\\\[distribute\\\\]\n```\n\nWe provide a developer version with additional pre-commit hooks to perform\nchecks compared to the official version:\n\n```bash\n# For windows\npip install -e .[dev]\n# For mac\npip install -e .\\\\[dev\\\\]\n\n# Install pre-commit hooks\npre-commit install\n```","tools":"## Available Tools\n\n1.  Easy-to-Use: Designed for developers, with fruitful components, comprehensive documentation, and broad compatibility. \n2.  High Robustness: Supporting customized fault-tolerance controls and retry mechanisms to enhance application stability.\n3.  Actor-Based Distribution: Building distributed multi-agent applications in a centralized programming manner for streamlined development.\n4.  ModelWrapper: Supports both local model services and third-party model APIs.\n5.  AgentScope Workstation: Provides a drag-and-drop programming platform and a copilot for beginners of AgentScope!\n6.  AgentScope Studio: Provides an easy-to-use runtime user interface capable of displaying multimodal output on the front end, including text, images, audio and video.\n7.  Web Search: Allows agents to search the web for information.\n8.  Data Query: Enables agents to query and retrieve data from various sources.\n9.  Retrieval: Supports information retrieval capabilities for agents.\n10. Code Execution: Allows agents to execute code snippets.\n11. File Operation: Enables agents to perform file-related operations.\n12. Text Processing: Provides text processing functionalities for agents.\n13. Multi Modality: Supports handling of multiple modalities of data.\n14. Wikipedia Search and Retrieval: Allows agents to search and retrieve information from Wikipedia.\n15. TripAdvisor Search: Enables agents to search for information on TripAdvisor.\n16. Web Browser Control: Allows agents to control and interact with web browsers.","faq":null,"created_at":"2024-01-12T03:41:59+00:00","updated_at":"2025-03-28T17:40:52+00:00","source_url":"https://model-context-protocol.com/clients/llm-multi-agent-application-building-framework","related_articles":[]}