88Z AI, 7 July — Shanghai AI Lab has released the open-source research agent workbench InternAgentS, designed specifically for the AI for Science domain. The platform supports local deployment and multi-model adaptation, integrating full-process functions such as paper reading, experiment analysis, code iteration, and scientific writing. It is compatible with domestic and private models like DeepSeek, Qwen, and Kimi, connecting to over 3,600 research tools and skills.
At a glance
- InternAgentS integrates full workflows like paper reading, analysis, and writing into a unified space
- Supports domestic models like DeepSeek and Qwen while connecting to over 3,600 research tools
The update
Shanghai Artificial Intelligence Laboratory has officially open-sourced InternAgentS, a domestic research agent workbench tailored for the AI for Science sector. This platform aims to provide researchers with a collaborative environment that supports local deployment and multi-model adaptation, ensuring data privacy and operational flexibility. InternAgentS integrates key stages of the scientific workflow, including literature review, experimental data analysis, code iteration, remote computing resource scheduling, and academic writing, into a unified project space. The platform supports integration with major domestic large language models such as DeepSeek, Qwen, and Kimi, as well as private models. Additionally, it connects with over 3,600 specialized research tools and Skills, enabling intelligent assistance across the entire chain from ideation to final output.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- 书生InternSource published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.