Website | Source
We design for increasingly agentic LLMs. Our approach leverages the models' reasoning and tool-use abilities rather than constraining them with strict prompts and opinionated orchestrations.
Why use AgentScope?
- Simple yet powerful: start building your agents in 5 minutes with built-in ReAct agent, tools, skills, human-in-the-loop steering, memory, planning, realtime voice, evaluation, model finetuning, etc.
- Extensible: large number of ecosystem integrations for tools, memory and observability; built-in support for protocols such as MCP, A2A and agent skills; message hub for flexible multi-agent orchestration and workflows.
- Production-ready：deploy and serve your agents locally, as serverless in the cloud, or on your K8s cluster with built-in OTel support and multi-language support.
From developing, observability to deployment, we provide an integrated suite of components:
- QwenPaw - Your Personal AI Assistant, supporting both local and cloud deployment.
- AgentScope - A flexible programming framework for building multi-agent applications with self-explanatory APIs.
- AgentScope-Runtime - Scalable deployment infrastructure for running agents reliably in production.
- AgentScope-Studio - Visual development environment for rapid prototyping, debugging, and monitoring your agents.
- AgentScope-Samples - A curated collection of ready-to-use agent examples and templates, from simple command-line tools to full-stack production-ready applications.
- Skills - A curated collection of skills around AgentScope ecosystem and QwenPaw applications.
Tags:
ai
llm
agent
jvm
Last modified 21 June 2026