InternAgentS - An open-source, domestically developed research intelligent agent workbench from Shanghai AI Lab.

What is InternAgentS?

InternAgentS is an open-source, domestically developed research intelligent agent workbench from the Shanghai AI Lab, designed for AI for Science scenarios. It integrates disparate processes such as paper reading, experimental analysis, code iteration, remote computing, and research writing into a unified project space. The platform supports multiple models including DeepSeek, Qwen, Kimi, GLM, Intern-S, and Claude, and can be deployed locally, ensuring the security of unpublished papers and experimental data. InternAgentS has integrated with over 3600 research tools and skills from SCP 2.0, covering six major academic disciplines, and supports the MCP protocol.

Main functions of InternAgentS

• Project Space Management: Organize papers, code, data, experimental results, scientific charts, and generated products around research projects to form a traceable research workflow.
• Literature Reading and Writing: The intelligent agent assists in completing literature reviews, methodological comparisons, report writing, and paper writing, and then returns the output to the project space.
• Experimental analysis and code iteration: It supports experimental analysis, code modification, result organization, and generation of interim conclusions.
• Remote computing: Connect to a remote Linux host, execute computational tasks after review and authorization by the researcher, and complete result collection and subsequent analysis.
• Multi-model access: Supports DeepSeek, Qwen, Kimi, GLM, Intern-S, Claude, and private model services deployed locally or on an institutional intranet.
• Tool ecosystem integration: Access to SCP 2.0's 3600+ research tools and skills, covering six major disciplines: biology, chemistry, physics, materials science, earth science, and mathematics and information science.
• Protocol compatibility: It supports SCP (Scientific Intelligence Context Protocol) and MCP protocol, facilitating the access of third-party tools.

Follow us on WeChat and reply with "open source",join inAI open source project discussion group

How to use InternAgentS

• Visit the official website: Visit the InternAgentS website at https://internagents.github.io/ to learn about the project and its documentation.
• Cloning repository: Clone the InternAgentS repository from GitHub to your local environment for installation and deployment.
• Create project space: Configure research projects and import papers, code, data, and related research materials.
• Configuration model: Select and connect the required AI model (domestic model, Claude model, or local private model).
• Access tools: Configure SCP/MCP connections to integrate research tools and skills.
• Initiate a task: In projects, intelligent agents can assist in tasks such as literature reading, experimental analysis, and code modification.
• Review and Authorization: Review the intermediate products generated by the intelligent agent, authorize remote computing tasks, and collect the analysis results.

InternAgentS's core advantages

• Domestically developed, open-source, and controllable: It is completely open source, supports local deployment, and ensures the security of scientific research data in university laboratories and enterprise R&D departments.
• Flexible adaptation to multiple models: It is not limited to a single model, but supports mainstream domestic and international models as well as local private models, thus avoiding vendor lock-in.
• Full project context: By integrating scattered research processes into a single workspace, a traceable, reusable, and iterative research workflow can be formed.
• Enrich the tool ecosystem: It integrates over 3,600 research tools and skills, deeply covering six major academic disciplines, far exceeding the number of tools available on a general AI workbench.
• Remote computing support: It can connect to a remote Linux host to perform computing tasks, making it suitable for high-performance computing and complex simulation scenarios.
• Protocol open: It supports both SCP and MCP protocols, facilitating community expansion and access for third-party tools, and enabling the construction of an open scientific research intelligence infrastructure.

InternAgentS project address

• Project official websitehttps://internagents.github.io/
• GitHub repositoryhttps://github.com/qzzqzzb/OpenClaudeScience

Comparison of InternAgentS with similar products

Application scenarios of InternAgentS

• Materials Science Analysis: Perform material property calculations, crystal structure analysis, and data mining to assist in the discovery and screening of new materials.
• Computational chemistry research: It can perform complex tasks such as molecular simulation, reaction pathway calculation, and quantum chemical calculation, such as caffeine molecule calculation.
• Engineering modeling and simulation: Establish physical models (such as Y-type microfluidic mixers and fan turbulence intensity analysis) and perform numerical simulations.
• Literature review and report writing: It automatically retrieves a large number of documents, extracts key information, and generates structured literature reviews and research reports.
• Interdisciplinary collaborative research: Integrate tools and data resources from different disciplines to support interdisciplinary research projects in fields such as biology, chemistry, and physics.