agentscope-aiagentscope-aiOfficialยท2 Agent Skills Included

agentscope

Build and deploy production-ready AI agents with one Python framework

Builds reasoning AI agents with tool use, memory, and structured output in Python. Connects agents to major LLM providers, MCP servers, and isolated sandboxes like Docker and Kubernetes. Removes the pain of wiring prompts, tool calls, and event streaming by hand. Ships ready examples for RAG, long-term memory, chat channels, and multi-agent pipelines.
npx skills add agentscope-ai/agentscope --all -g -y

All Skills in This Repository (2)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install AgentScope?โ–ผ

Run `npx skills add agentscope-ai/agentscope --all -g -y` in your terminal to install all tools in this suite globally.

What is AgentScope used for?โ–ผ

AgentScope is a Python framework for building production-ready AI agents with reasoning loops, tool calling, memory, and sandboxed code execution.

Which LLM providers does AgentScope support?โ–ผ

It works with OpenAI, Anthropic, Gemini, DashScope, DeepSeek, Moonshot, xAI, and Ollama, plus embedding and text-to-speech models.

Can AgentScope run code safely in a sandbox?โ–ผ

Yes. It supports isolated execution through Docker, Kubernetes, E2B, Daytona, Bubblewrap, and Apple Container workspaces.

Does AgentScope support multi-agent workflows?โ–ผ

Yes. Its pipeline feature runs multiple agents behind one event stream, and it connects agents to Discord, Feishu, and DingTalk channels.

Related Repositories in Software Engineering

View All in Software Engineeringโ†’