Pegasus AI
Next-Gen Workflows
Funded by the National Science Foundation · Award #2513101
Next-generation workflow management — intelligent automation, real-time monitoring, and LLM-powered tools for large-scale scientific computing.
Funded by the National Science Foundation · Award #2513101
PegasusAI is the next-generation AI-driven scientific workflow management system developed by a multi-institutional team funded by the U.S. National Science Foundation.
Open Workflows
Institutions
Funded Research
ML models predict resource needs and optimize execution.
Real-time anomaly detection and automatic plan adjustment.
AI-augmented tools for creation, monitoring, and debugging.
Curated datasets to advance cyberinfrastructure research.
Pegasus AI acts as the intelligent orchestration layer across the scientific computing continuum. By bridging human intent with distributed resources, it creates a seamless flow between data generation and large-scale execution.
Five integrated research threads that together make Pegasus workflows faster, smarter, and more accessible.
ML models that predict task runtime, memory usage, and resource needs to enable smarter scheduling decisions.
Real-time performance tracking that detects anomalies, surfaces bottlenecks, and supports live workflow introspection.
LLM-powered tools that help scientists compose, validate, and refine scientific workflows through natural language.
Educational integration of Pegasus AI into academic curricula, enabling students to engage with real-world scientific computing.
Implemented within Pegasus's modular architecture to ensure compatibility with the NSF cyberinfrastructure ecosystem.
Real-world Pegasus AI pipelines — open source, runnable today
Air quality sensor data ingestion and analysis at regional scale.
pegasus-isi/airquality-workflowSketch and prototype Pegasus AI workflows from a minimal starting point.
pegasus-isi/napkin-vibe-exampleLarge-scale NCBI Sequence Read Archive search using distributed execution.
pegasus-isi/sra-searchSeismic data processing and ground motion analysis across HPC infrastructure.
pegasus-isi/earthquake-workflowSatellite imagery ML pipeline for monitoring agricultural crop health.
pegasus-isi/crophealth-workflowCentralized hub for discovering and sharing Pegasus AI workflows.
pegasushub.ioA walkthrough of the interface — project setup, workflow visualization, and job monitoring.
Peer-reviewed work from the Pegasus AI research program, funded by NSF award #2513101.
Multi-institutional collaborators across the NSF ecosystem
Research · Updates · Insights
