SEARCH · Search NASA

Results for “Workflow management systems”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 145 records · Page 8

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Portable, heterogeneous ensemble workflows at scale using libEnsemble

libEnsemble is a Python-based toolkit for running dynamic ensembles, developed as part of the DOE Exascale Computing Project. The toolkit utilizes a unique generator–simulator–allocator paradigm, where generators produce input for simulators, simulators evaluate those inputs, and allocators decide whether and when a simulator or generator should be called. The generator steers the ensemble based on simulation results. Generators may, for example, apply methods for numerical optimization, machine learning, or statistical calibration. libEnsemble communicates between a manager and workers. Flexibility is provided through multiple manager–worker communication substrates each of which has different benefits. These include Python’s multiprocessing, mpi4py, and TCP. Multisite ensembles are supported using Balsam or Globus Compute. We overview the unique characteristics of libEnsemble as well as current and potential interoperability with other packages in the workflow ecosystem. We highlight libEnsemble’s dynamic resource features: libEnsemble can detect system resources, such as available nodes, cores, and GPUs, and assign these in a portable way. These features allow users to specify the number of processors and GPUs required for each simulation; and resources will be automatically assigned on a wide range of systems, including Frontier, Aurora, and Perlmutter. Such ensembles can include multiple simulation types, some using GPUs and others using only CPUs, sharing nodes for maximum efficiency. We also describe the benefits of libEnsemble’s generator–simulator coupling, which easily exposes to the user the ability to cancel, and portably kill, running simulations based on models that are updated with intermediate simulation output. We demonstrate libEnsemble’s capabilities, scalability, and scientific impact via a Gaussian process surrogate training problem for the longitudinal density profile at the exit of a plasma accelerator stage. In conclusion, the study uses gpCAM for the surrogate model and employs either Wake-T or WarpX simulations, highlighting efficient use of resources that can easily extend to exascale.

Dynamic ensembles↗

DOE OSTI2024

DIRAC current, upcoming and planned capabilities and technologies

DIRAC is the interware for building and operating large scale distributed computing systems. It is adopted by multiple collaborations from various scientific domains for implementing their computing models. DIRAC provides a framework and a rich set of ready-to-use services for Workload, Data and Production Management tasks of small, medium and large scientific communities having different computing requirements. The base functionality can be easily extended by custom components supporting community specific workflows. DIRAC is at the same time an aging project, and a new DiracX project is taking shape for replacing DIRAC in the long term. This contribution will highlight DIRAC’s current, upcoming and planned capabilities and technologies, and how the transition to DiracX will take place. Examples include, but are not limited to, adoption of security tokens and interactions with Identity Provider services, integration of Clouds and High Performance Computers, interface with Rucio, improved monitoring and deployment procedures.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2011

The Challenges of Releasing Human Data for Analysis

The NASA Johnson Space Center s (NASA JSC) Committee for the Protection of Human Subjects (CPHS) recently approved the formation of two human data repositories: the Lifetime Surveillance of Astronaut Health Repository (LSAH-R) for clinical data and the Life Sciences Data Archive Repository (LSDA-R) for research data. The establishment of these repositories forms the foundation for the release of data and information beyond the scope for which the data was originally collected. The release of clinical and research data and information is primarily managed by two NASA groups: the Evidence Base Working Group (EBWG), consisting of members of both repositories, and the LSAH Policy Board. The goal of unifying these repositories and their processes is to provide a mutually supportive approach to handling medical and research data, to enhance the use of medical and research data to reduce risk, and to promote the understanding of space physiology, countermeasures and other mitigation strategies. Over the past year, both repositories have received over 100 data and information requests from a wide variety of requesters. The disposition of these requests has highlighted the challenges faced when attempting to make data collected on a unique set of subjects available beyond the original intent for which the data were collected. As the EBWG works through each request, many considerations must be factored into account when deciding what data can be shared and how - from the Privacy Act of 1974 and the Health Insurance Portability and Accountability Act (HIPAA), to NASA s Health Information Management System (10HIMS) and Human Experimental and Research Data Records (10HERD) access requirements. Additional considerations include the presence of the data in the repositories and vetting requesters for legitimacy of their use of the data. Additionally, fair access must be ensured for intramural, as well as extramural investigators. All of this must be considered in the formulation of the charters, policies and workflows for the human data repositories at NASA.

Fitts, Mary↗

NASA NTRS2019

Collecting and Processing Earth Science Data Metrics at NASA ESDIS

Since the launch of Terra satellite in 1999, the number of Earth Science remote sensing data products created and distributed by NASA's Earth Observing System (EOS) Data and Information System (EOSDIS) has increased from a few hundred to nearly ten thousand. NASA's Earth Science Data and Information System (ESDIS) Metrics System (EMS) collects metrics on data ingest, archive, and distribution by its Distributed Active Archive Centers (DAACs) and the Science Investigator-led Systems (SIPS), known as Data Providers. These metrics are critical in helping NASA management as well as data producers in resource planning and gaining a wide range of knowledge of data users and data usage.EMS receives flat files, or log files of data archive, ingest, and distribution either in their raw format, such as Apache web logs, or text files of log records formatted by the Data Providers. Tens of millions of records are processed each day to extract metrics on data products, user information, distribution protocols and services, and so on. The metrics are then made available to designated parties.This presentation provides an overview of the EMS processing workflow and improvement efforts made in recent years to handle ever-increasing number of data records and new metrics requirements, discusses several key steps including mapping log records to data products and identifying user communities along with geo-distribution, and demonstrates typical metrics capabilities produced by the EMS system. Challenges and potential approaches to improve the system are also discussed.

Pan, Jianfu↗

NASA NTRS2021

Southwest Water Resources: Monitoring Surface Water Extents of Remote Stock Ponds in the Southwestern United States Using Earth Observing Systems for Enhanced Water Resources Management

Due to increasingly frequent and severe drought conditions in the southwestern US, land managers and livestock producers need to monitor stock ponds with increasing regularity. The ability to assess stock pond water levels with Earth observing satellite systems would enhance monitoring efforts of partners at the US Forest Service, Arizona Department of Game and Fish, and the Diablo Trust. This study employed Landsat 8 Operational Land Imager (OLI), Sentinel-1 C-band Synthetic Aperture Radar (C-SAR), and Sentinel-2 Multispectral Instrument (MSI) to monitor surface water extent for hundreds of critical stock ponds in Arizona. Using methods adapted from previously developed image processing workflows, this project conducted a time-series analysis to capture seasonal and interannual variations in surface water area between 2013 to 2021. In addition, end users can monitor the surface water extent of stock ponds through the developed Google Earth Engine software tool called Surface Water Identification and Forecasting Tool (SWIFT). SWIFT incorporates the Automated Water Extraction Index, Modified Normalized Difference Water Index, and Tasseled Cap-Wetness Index for optical imagery and the incidence angle, VV and VH polarization bands for Sentinel-1 imagery to detect small water bodies in the study area with an overall accuracy range of 88-93%. These tools will empower our partners to monitor the extents of water in their stock ponds remotely, enabling them to develop data-informed and sustainable management solutions for decades to come.

Rainey Aberle↗

NASA NTRS2007

Collaborative Resource Allocation

Collaborative Resource Allocation Networking Environment (CRANE) Version 0.5 is a prototype created to prove the newest concept of using a distributed environment to schedule Deep Space Network (DSN) antenna times in a collaborative fashion. This program is for all space-flight and terrestrial science project users and DSN schedulers to perform scheduling activities and conflict resolution, both synchronously and asynchronously. Project schedulers can, for the first time, participate directly in scheduling their tracking times into the official DSN schedule, and negotiate directly with other projects in an integrated scheduling system. A master schedule covers long-range, mid-range, near-real-time, and real-time scheduling time frames all in one, rather than the current method of separate functions that are supported by different processes and tools. CRANE also provides private workspaces (both dynamic and static), data sharing, scenario management, user control, rapid messaging (based on Java Message Service), data/time synchronization, workflow management, notification (including emails), conflict checking, and a linkage to a schedule generation engine. The data structure with corresponding database design combines object trees with multiple associated mortal instances and relational database to provide unprecedented traceability and simplify the existing DSN XML schedule representation. These technologies are used to provide traceability, schedule negotiation, conflict resolution, and load forecasting from real-time operations to long-range loading analysis up to 20 years in the future. CRANE includes a database, a stored procedure layer, an agent-based middle tier, a Web service wrapper, a Windows Integrated Analysis Environment (IAE), a Java application, and a Web page interface.

Wang, Yeou-Fang↗

NASA NTRS2024

Optimizing Sample Collection and Accessibility through the Biospecimen and Tissue Sharing Collection (BTSC) Program

The Space Radiation Element (SRE) of the Human Research Program (HRP) is dedicated to establishing a robust biospecimen and tissue sharing collection (BTSC) program that enhances sample collection, tracking, access, distribution, and usability, with the goal of maximizing scientific return. By leveraging biospecimens and tissues from previous experiments, HRP effectively achieves its scientific objectives in characterizing and mitigating the human health impacts of spaceflight while optimizing resource utilization. To further improve the usability and accessibility of the current biospecimen archive, the project aims to expand upon NASA's existing resources and institutional knowledge, ensuring ongoing modernization. To facilitate seamless navigation of the program's workflow, an educational series on the BTSC program is provided to Principal Investigators (PIs). This comprehensive series equips PIs with crucial information on submitting their inventory via the BTSC Metadata Intake Form, ultimately leading to the public availability of their data on NASA's Life Science Portal (NLSP). Covering various aspects such as metadata submission instructions and backend processes for transferring metadata to the Laboratory Information Management System (LIMS), the series incorporates guidance from NASA's Biological Institutional Scientific Collection (NBISC) and Ames Life Sciences Data Archive (ALSDA). The BTSC program represents a significant stride towards enhancing the usability and accessibility of biospecimens for space research. By enabling NASA to deepen its understanding of the health implications of long-term spaceflight, this initiative plays a pivotal role in ensuring the safety and well-being of astronauts.

Shelita Renee Augustus↗

DOE OSTI2024

VerifyIO: Ensuring Correctness of Consistency Semantics in Parallel I/O

Abstract—High-performance computing (HPC) applications generate and consume substantial amounts of data, typically managed by parallel file systems. These applications access file systems either through the POSIX interface or by using highlevel I/O libraries. While the POSIX consistency model remains dominant in HPC, emerging file systems and popular I/O libraries increasingly adopt alternative consistency models that relax semantics in various ways, creating significant challenges for correctness and portability. This paper addresses these challenges by proposing a trace-driven I/O consistency verification workflow, implemented in our open-source tool, VerifyIO, which collects execution traces, detects data conflicts, and verifies proper synchronization against specified consistency models. Our extensive evaluation of 91 test case executions across three widely used I/O libraries with four I/O consistency models reveals critical consistency issues at both application and implementation levels.

Consistency Semantics↗

NASA NTRS2015

Developing a Business Intelligence Process for a Training Module in SharePoint 2010

Prior to this project, training information for the employees of the National Center for Critical Processing and Storage (NCCIPS) was stored in an array of unrelated spreadsheets and SharePoint lists that had to be manually updated. By developing a content management system through a web application platform named SharePoint, this training system is now highly automated and provides a much less intensive method of storing training data and scheduling training courses. This system was developed by using SharePoint Designer and laying out the data structure for the interaction between different lists of data about the employees. The automation of data population inside of the lists was accomplished by implementing SharePoint workflows which essentially lay out the logic for how data is connected and calculated between certain lists. The resulting training system is constructed from a combination of five lists of data with a single list acting as the user-friendly interface. This interface is populated with the courses required for each employee and includes past and future information about course requirements. The employees of NCCIPS now have the ability to view, log, and schedule their training information and courses with much more ease. This system will relieve a significant amount of manual input and serve as a powerful informational resource for the employees of NCCIPS in the future.

Schmidtchen, Bryce↗

DOE OSTI2025

Node-red Software Architecture For Soec System Control

The software workflows that have been developed are open-source and therefore can be accessed and utilized by researchers and students all around the world for free of cost. The software is flexible and easily modifiable to suit the needs for testing bench-scale to system-level setups, and is not limited to just hydrogen generation facilities. The web-interface of the code allows for easy remote access and management, which is especially useful for distributed systems. This is more challenging with traditional PLCs, which often require direct connections or specialized software, making remote troubleshooting more cumbersome. Additionally, since the underlying interface is open-source, with an active community contributing to its development, regular updates, new features, and a wealth of community support and shared solutions will keep improving the overall architecture without excessive fees for upgrades.

Shigrekar, Amey [Idaho National Laboratory (INL), ↗

NASA NTRS2011

Generic, Extensible, Configurable Push-Pull Framework for Large-Scale Science Missions

The push-pull framework was developed in hopes that an infrastructure would be created that could literally connect to any given remote site, and (given a set of restrictions) download files from that remote site based on those restrictions. The Cataloging and Archiving Service (CAS) has recently been re-architected and re-factored in its canonical services, including file management, workflow management, and resource management. Additionally, a generic CAS Crawling Framework was built based on motivation from Apache s open-source search engine project called Nutch. Nutch is an Apache effort to provide search engine services (akin to Google), including crawling, parsing, content analysis, and indexing. It has produced several stable software releases, and is currently used in production services at companies such as Yahoo, and at NASA's Planetary Data System. The CAS Crawling Framework supports many of the Nutch Crawler's generic services, including metadata extraction, crawling, and ingestion. However, one service that was not ported over from Nutch is a generic protocol layer service that allows the Nutch crawler to obtain content using protocol plug-ins that download content using implementations of remote protocols, such as HTTP, FTP, WinNT file system, HTTPS, etc. Such a generic protocol layer would greatly aid in the CAS Crawling Framework, as the layer would allow the framework to generically obtain content (i.e., data products) from remote sites using protocols such as FTP and others. Augmented with this capability, the Orbiting Carbon Observatory (OCO) and NPP (NPOESS Preparatory Project) Sounder PEATE (Product Evaluation and Analysis Tools Elements) would be provided with an infrastructure to support generic FTP-based pull access to remote data products, obviating the need for any specialized software outside of the context of their existing process control systems. This extensible configurable framework was created in Java, and allows the use of different underlying communication middleware (at present, both XMLRPC, and RMI). In addition, the framework is entirely suitable in a multi-mission environment and is supporting both NPP Sounder PEATE and the OCO Mission. Both systems involve tasks such as high-throughput job processing, terabyte-scale data management, and science computing facilities. NPP Sounder PEATE is already using the push-pull framework to accept hundreds of gigabytes of IASI (infrared atmospheric sounding interferometer) data, and is in preparation to accept CRIMS (Cross-track Infrared Microwave Sounding Suite) data. OCO will leverage the framework to download MODIS, CloudSat, and other ancillary data products for use in the high-performance Level 2 Science Algorithm. The National Cancer Institute is also evaluating the framework for use in sharing and disseminating cancer research data through its Early Detection Research Network (EDRN).

Foster, Brian M.↗

NASA NTRSDate not supplied

Application of Agile for Systems Engineering, Project Management and Modeling and Lessons Learned

The Systems Engineering team within the Human Research Program (HRP) Exploration Medical Capability (ExMC) Element has been transforming its development processes to be more efficient, robust,and responsive to change and to its stakeholders. To these ends, the Systems Engineering team trialed the integration of agile development techniques into existing and new processes. Agile development methods are well understood within the software development community. Outside ofsoftware development, however, how non-software project management (PM) and systems engineering (SE) teams implement agile development techniques is less well understood. In its transformation efforts, the ExMC SE team focused on three main areas: Improving the project communications among subsystem teams and stakeholders by adopting a scrum-like process, Changing the status and reporting mechanisms to improve schedule coordination between the subsystem team, SE leadership, and ExMC Element leadership, and Unifying the model-based SE workflow to improve understanding of Concepts of Operations across projects.This presentation highlights several of these transformations and what the SE team learned while undergoing the transformation.

S Lumpkins↗

DOE OSTI2025

Computational Performance Bounds Prediction in Quantum Computing With Unstable Noise

Quantum computing has significantly advanced in recent years, boasting devices with hundreds of quantum bits (qubits), hinting at its potential quantum advantage over classical computing. Yet, noise in quantum devices poses significant barriers to realizing this supremacy. Understanding noise’s impact is crucial for reproducibility and application reuse; moreover, the next-generation quantum-centric supercomputing essentially requires efficient and accurate noise characterization to support system management (e.g., job scheduling), where ensuring correct functional performance (i.e., fidelity) of jobs on available quantum devices can even be higher-priority than traditional objectives. However, noise fluctuates over time, even on the same quantum device, which makes predicting the computational bounds for on-the-fly noise is vital. Noisy quantum simulation can offer insights but faces efficiency and scalability issues. Here, in this work, we propose a data-driven workflow, namely QuBound, to predict computational performance bounds. It decomposes historical performance traces to isolate noise sources and devises a novel encoder to embed circuit and noise information processed by a Long Short-Term Memory (LSTM) network. For evaluation, we compare QuBound with a state-of-the-art learning-based predictor, which only generates a single performance value instead of a bound. Experimental results show that the result of the existing approach falls outside of performance bounds, while all predictions from our QuBound with the assistance of performance decomposition better fit the bounds. Moreover, QuBound can efficiently produce practical bounds for various circuits with over 106 speedup over simulation; in addition, the range from QuBound is over 10× narrower than the state-of-the-art analytical approach.

Li, Jinyang [George Mason Univ., Fairfax, VA (Unit↗

DOE OSTI2026

Evaluation of AI-enabled Digital Documented Safety Analysis

The National Reactor Innovation Center (NRIC) is leading a transformative initiative to accelerate advanced reactor deployment by fundamentally reimagining how nuclear safety basis documentation is developed, reviewed, and maintained. Traditional Documented Safety Analysis (DSA) processes for DOE-authorized facilities rely on static, document-centric workflows that consume significant time and resources, exemplified by recent major licensing efforts requiring hundreds of thousands of staff hours and millions of pages of documentation review. These conventional approaches create barriers to the rapid, cost-effective deployment of advanced reactors that America's future energy needs demand. NRIC's DOE Authorization Digital Transformation Project addresses these challenges through an innovative framework that integrates artificial intelligence (AI), digital engineering, and systems-based data management into a cohesive digital ecosystem. This white paper presents NRIC's methodology for evaluating AI-enabled document generation capabilities within this broader digital infrastructure, using the Demonstration of Microreactor Experiments (DOME) facility as a pilot case study. The evaluation will assess an AI tool's ability to generate a Preliminary Documented Safety Analysis (PDSA) through progressive integration stages—from standalone document processing to full digital thread connectivity—while maintaining rigorous verification, validation, and regulatory acceptance standards. By establishing dynamic, traceable connections between design data and safety documentation, NRIC's approach has the potential to reduce both document development time and regulatory review cycles by as much as 50%, while simultaneously improving accuracy, consistency, and traceability. This initiative represents a critical step toward establishing reusable digital infrastructure that reactor developers can leverage to accelerate their path from concept to commercial operation, directly supporting NRIC's mission to demonstrate and deploy advanced nuclear energy technologies.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2025

HEPTAPOD: Orchestrating High Energy Physics Workflows Towards Autonomous Agency

Many workflows in high-energy-physics (HEP) stand to benefit from recent advances in transformer-based large language models (LLMs). While early applications of LLMs focused on text generation and code completion, modern LLMs now support orchestrated agency: the coordinated execution of complex, multi-step tasks through tool use, structured context, and iterative reasoning. We introduce the HEP Toolkit for Agentic Planning, Orchestration, and Deployment (HEPTAPOD), an orchestration framework designed to bring this emerging paradigm to HEP pipelines. The framework enables LLMs to interface with domain-specific tools, construct and manage simulation workflows, and assist in common utility and data analysis tasks through schema-validated operations and run-card-driven configuration. To demonstrate these capabilities, we consider a representative Beyond the Standard Model (BSM) Monte Carlo validation pipeline that spans model generation, event simulation, and downstream analysis within a unified, reproducible workflow. HEPTAPOD provides a structured and auditable layer between human researchers, LLMs, and computational infrastructure, establishing a foundation for transparent, human-in-the-loop systems.

Menzo, Tony [Alabama U.; Fermilab] (ORCID:00000002↗

DOE OSTI2026

TRACE Input Modernization

This work presents a Tom’s Obvious Minimal Language (TOML)-based representation of input for the US Nuclear Regulatory Commission’s TRAC/RELAP Advanced Computational Engine (TRACE) thermal hydraulics code. Implemented using the Workbench Analysis Sequence Processor (WASP), the approach maps traditional TRACE input structures to a hierarchical format composed of named parameters, typed values, and native data collections. The resulting representation preserves TRACE’s existing modeling capabilities while providing a modern, structured interface for model development and management. WASP further extends TOML through a file import directive that supports modular model composition and reusable input organization. In addition, WASP provides extended array data entry convenience with various data repeat and interpolation capabilities. Examples of the new TOML syntax are provided for major TRACE input categories, including hydraulic components, heat structures, control systems, and trip logic. The TOML representation establishes a foundation for improved validation, tooling, automation, and model maintainability while remaining compatible with existing TRACE workflows. To facilitate migration to the TOML-based input format, the TRACE executable now supports conversion of native TRACE input into an intermediate JSON representation. A Python utility subsequently transforms the JSON data into an equivalent TOML model. Lastly, the TRACE executable now supports execution using TOML-formatted input.

Lefebvre, Robert A. [Oak Ridge National Laboratory↗

DOE OSTI2025

WRF-ELM v1.0: a regional climate model to study land–atmosphere interactions over heterogeneous land use regions

Abstract. The Energy Exascale Earth System Model (E3SM) Land Model (ELM) is a state-of-the-art land surface model that simulates the intricate interactions between the terrestrial land surface and other components of the Earth system. Originating from the Community Land Model (CLM) version 4.5, ELM has been under active development, with added new features and functionality, including plant hydraulics, radiation–topography interaction, subsurface multiphase flow, and more explicit land use and management practices. This study integrates ELM v2.1 with the Weather Research and Forecasting (WRF; WRF-ELM) model through a modified Lightweight Infrastructure for Land Atmosphere Coupling (LILAC) framework, enabling affordable high-resolution regional modeling by leveraging ELM's innovative features alongside WRF's diverse atmospheric parameterization options. This framework includes a top-level driver for variable communication between WRF and ELM and Earth System Modeling Framework (ESMF) caps for the WRF atmospheric component and ELM workflow control, encompassing initialization, execution, and finalization. Importantly, this LILAC–ESMF framework demonstrates a more modular approach compared to previous coupling efforts between WRF and land surface models. It maintains the integrity of ELM's source code structure and facilitates the transfer of future developments in ELM to WRF-ELM. To test the ability of the coupled model to capture land–atmosphere interactions over regions with a variety of land uses and land covers, we conducted high-resolution (4 km) WRF-ELM ensemble simulations over the Great Lakes region (GLR) in the summer of 2018 and systematically compared the results against observations, reanalysis data, and WRF-CTSM (WRF coupled with the Community Terrestrial Systems Model). In general, the coupled WRF-ELM model has reasonably captured the spatial distribution of surface state variables and fluxes across the GLR, particularly over the natural vegetation areas. The evaluation results provide a baseline reference for further improvements in ELM in the regional application of high-resolution weather and climate predictions. Our work serves as an example to the model development community for expanding an advanced land surface model's capability to represent fully-coupled land–atmosphere interactions at fine spatial scales. The development and release of WRF-ELM marks a significant advancement for the ELM user community, providing opportunities for fine-scale regional representation, parameter calibration in coupled mode, and examination of new schemes with atmospheric feedback.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

An Open-source Llm Enhanced-tool Specialized In Helping Moose Related Problems And Tasks

MOOSEenger is an open-source, terminal-first chat application for the MOOSE ecosystem that couples specialized parsing of MOOSE documentation and “.i” input files with retrieval-augmented generation to deliver grounded answers about multiphysics modeling and workflows. It includes dedicated readers for MOOSE-style HTML and a pyhit-based parser that uses the MOOSE syntax tree to preserve block structure and attach retrieval metadata. A data-ingestion pipeline performs semantic chunking into atomic facts and stores them hierarchically in a local Chroma vector database that maintains parent–child relationships across documents; the system can ingest directories, individual files, and single-page web content, and it provides CRUD operations (insert, update, delete) to manage the corpus. At query time, relevant chunks are embedded, retrieved, and fused into the model context, with interactive features such as token streaming, persistent chat history, and dynamic RAG (retrieval triggered by user input or intermediate model output). Deployment is flexible: MOOSEenger runs with local Ollama models or remote Hugging Face/OpenAI backends—typically coordinating generation, lightweight tagging/summarization, and embeddings across three models—and it also supports a server mode and integration with the VS Code Continue interface.

Li, Mengnan [Idaho National Laboratory (INL), Idah↗