Deploy-Master: Automating the Deployment of 50,000+ Agent-Ready Scientific Tools in One Day
Yi Wang, Zhenting Huang, Zhaohan Ding, Ruoxue Liao, Yuan Huang, Xinzijian Liu, Jiajun Xie, Siheng Chen, Linfeng Zhang

TL;DR
Deploy-Master automates large-scale discovery, validation, and deployment of over 50,000 scientific tools in a single day, enhancing reproducibility and integration into AI-driven workflows.
Contribution
It introduces a scalable, automated workflow for transforming open-source repositories into executable, containerized scientific tools with validation and registration at unprecedented scale.
Findings
Successfully deployed 50,112 tools in one day
Characterized deployment throughput, costs, and failure modes at scale
Enabled searchable registration of tools for reuse
Abstract
Open-source scientific software is abundant, yet most tools remain difficult to compile, configure, and reuse, sustaining a small-workshop mode of scientific computing. This deployment bottleneck limits reproducibility, large-scale evaluation, and the practical integration of scientific tools into modern AI-for-Science (AI4S) and agentic workflows. We present Deploy-Master, a one-stop agentic workflow for large-scale tool discovery, build specification inference, execution-based validation, and publication. Guided by a taxonomy spanning 90+ scientific and engineering domains, our discovery stage starts from a recall-oriented pool of over 500,000 public repositories and progressively filters it to 52,550 executable tool candidates under license- and quality-aware criteria. Deploy-Master transforms heterogeneous open-source repositories into runnable, containerized capabilities grounded…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsScientific Computing and Data Management · Multi-Agent Systems and Negotiation · Machine Learning in Materials Science
