core vs Qwen-Agent
Python frameworks for building AI agents compared
core and Qwen-Agent are Python frameworks for building conversational agents and tool-using applications. core runs an agent as a service with a local UI and REST API, while Qwen-Agent focuses on Qwen-based applications with reusable tools and runnable examples.

core: Build and Extend AI Agents
Cheshire Cat AI is a Python framework and microservice for building conversational AI agents. It is aimed at learning, research, and publishing agents, with a local UI and REST API for exploring and extending them.

Qwen-Agent: Build Tool-Using LLM Applications
Qwen-Agent is a Python framework for building Qwen-based assistants that can call tools, plan tasks, and work with documents. Use it to prototype or deploy agent applications when you need integrations such as MCP, code execution, or retrieval-augmented generation.
| core | Qwen-Agent | |
|---|---|---|
| Language | Python | Python |
| License | GPL-3.0 | Apache-2.0 |
| Stars | 3.1k | 17.1k |
| Forks | 411 | 1.7k |
| Last analyzed | Oct 3, 2026 | Oct 3, 2026 |
Key differences
- core provides a local UI, REST API, and API playground for interacting with an agent service; Qwen-Agent offers an optional Gradio GUI alongside its application framework.
- Qwen-Agent includes built-in assistants and examples for parallel function calls, document retrieval, browser assistance, and code execution; core highlights plugins and topics including vector search and MCP.
- Qwen-Agent requires access to a model service such as DashScope or a compatible endpoint; core is described as a locally installable Python service.
- core is licensed under GPL-3.0, while Qwen-Agent is licensed under Apache-2.0.
- core warns that version 2 is an unstable alpha with breaking changes and is not yet recommended for production; Qwen-Agent cautions that its code interpreter has basic isolation and its Python executor example is not sandboxed.
- Qwen-Agent is oriented toward building applications around Qwen models; core is positioned for learning, research, and publishing conversational agents.
Choose core if you…
- want a local agent service with a browser UI, REST API, and API playground.
- need a framework positioned for learning, research, or publishing conversational agents.
- want to explore plugin-based extensions or topics such as vector search and MCP.
Choose Qwen-Agent if you…
- need to build applications around Qwen models with tools, task planning, or document workflows.
- want examples for MCP, browser assistance, or code execution.
- need reusable agent components and can provide access to a compatible model service.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.