Jenny Chen
Jenny Chen
> Is this like some copilot robot? Yeah, I feel like it is.
感谢您的建议，我们会尽快安排
Thanks for sharing! I’ll take a look and see whether it can be integrated.
你好，感谢关注！ 目前 mirothinker 仓库主要聚焦于 deep research 相关 benchmark 的性能评测。考虑到开源社区的实际使用需求，我们近期计划做一些易用性提升： * 开源 MiroThinker v1.5 的用户体验优化版本模型权重； * 完善 MiroThinker 与 LobeChat 的整合； * 提供可生成与官网一致的 deep research report 的代码。 这些更新会在接下来的几天内陆续推出，敬请期待！ --- Hi, thanks...
> 代码只有google搜索，没有信息爬取 有信息爬取工具的，demo上用到的工具搜索、网页爬取、代码工具都开源了 搜索：https://github.com/MiroMindAI/MiroThinker/blob/main/libs/miroflow-tools/src/miroflow_tools/dev_mcp_servers/search_and_scrape_webpage.py 信息爬取：https://github.com/MiroMindAI/MiroThinker/blob/main/libs/miroflow-tools/src/miroflow_tools/dev_mcp_servers/jina_scrape_llm_summary.py 代码：https://github.com/MiroMindAI/MiroThinker/blob/main/libs/miroflow-tools/src/miroflow_tools/mcp_servers/python_mcp_server.py
> 有单独使用jina搜索的效果吗？目前看是需要同时用google.serper 和jina，不知道单独用jina的性能是不是会衰减多少，太穷了，用不起google 用jina的搜索应该也可以，就是现在没实现这个工具，可以让cursor写一个
Hello, thank you for your interest. Our current release is based on the standard Qwen3 architecture, with additional post-training for search agent functionality. Deployment can be done by following the...
Hi, thank you for your interest! We open-sourced some SFT/RL datasets a few months ago. MiroThinker v1.5 also uses internal synthetic/curated questions and trajectories, which we’re not planning to release...
Hi, I’ve just finished a major refactor of the Gradio demo today. Would you like to try the new version?
我们用的是Qwen3-14B或者gpt5-nano，效果差不多