IOWARP / DEMONSTRATIONS

See the stack at work.

For anyone who wants to see the software run: recordings of CLIO software on real scientific data and systems, made by the IOWarp team. The 2026 series follows the full stack, from CUDA kernels to DOE laboratory workflows; each entry states what its recording will show. The 2025 archive holds the first agent workflows on EarthScope, LAMMPS, ParaView, ADIOS2, and Slurm.

2026 series
Planned recordings across the stack
2025 archive
Recorded agent workflows
Research
The questions behind the demos
01 / Latest · 2026

The 2026 series.

These entries are placeholders, not previews. Each video appears here when it is published.

  1. 01 · To be recorded

    Zero to agent with CLIO Kit

    A clean machine to a working scientific agent: install CLIO Kit, connect an MCP client, and open a real HDF5 dataset.

  2. 02 · To be recorded

    EarthScope through the National Data Platform, 2026

    The NDP workflow rebuilt on the current releases: catalog search, staging, profiling, and plotting of GNSS data.

  3. 03 · To be recorded

    The HPC operator

    An agent submits and watches Slurm jobs, then reads the Darshan I/O profile to explain what the job did to the file system.

  4. 04 · To be recorded

    GPU payload offload

    CUDA kernels in CLIO Core write GPU-resident data into IOWarp and stage it through host memory and NVMe.

  5. 05 · To be recorded

    CLIO on DeltaAI and Aurora

    One Jarvis pipeline description deploys the same CLIO Core configuration on DeltaAI at NCSA and Aurora at Argonne.

  6. 06 · To be recorded

    Materio for materials research

    A materials question becomes a synthesis of the supplied literature, a map of the available lab, and a reviewed research plan.

  7. 07 · To be recorded

    Memory across sessions

    CLIO Agent resumes a data investigation days later and recalls what it learned and where the data lives.

  8. 08 · To be recorded

    DOE Genesis: SPOTTER-AI and PORTUS

    CLIO Agent investigating provenance with the SPOTTER-AI team at Argonne, and CLIO Coder fleets working with the PORTUS team at PNNL.

  9. 09 · To be recorded

    Fleet dispatch on a cluster

    CLIO Coder spreads bounded engineering tasks across workers on cluster nodes and returns reviewable run receipts.

02 / Archive · 2025

The 2025 archive.

Recorded between September and November 2025. Select a preview to load the video player.

OCT 20, 2025 / TOOL ORCHESTRATION

HPC workflow automation

An agent connects Slurm, ADIOS2, Jarvis, and a Gray–Scott simulation into one automated HPC workflow.

NOV 18, 2025 / VISUALIZATION

ParaView as an agent tool

ParaView exposed through an MCP server so an agent can build and adjust a scientific visualization.

SEP 29, 2025 / AGENT WORKFLOW

An IOWarp workflow end to end

An agent works through a scientific analysis with the IOWarp MCP servers, from data access to a finished plot.

SEP 29, 2025 / SCIENTIFIC FORMATS

ADIOS2 data through MCP

An agent reads and inspects ADIOS2 simulation output through the IOWarp MCP servers.

SEP 29, 2025 / DEPLOYMENT

Reproducible deployment

A workflow deployed reproducibly, with the agent’s activity streamed to a dashboard for inspection.

Jaime Cernuda · Jarvis, CLIO KitOpen on YouTube: Reproducible deployment ↗
Diagram of a six-stage materials science workflow: download a tomography dataset, reconstruct and segment the image stack, convert and store the volume, then visualize the result
2025 demo work / Materials workflow

Follow the data.

The six-stage materials workflow that the demonstrations aim to cover: from a tomography dataset to reconstruction, segmentation, storage, and visualization. Every handoff between tools is part of the scientific work.

The materials science story

What changed since

From tools to a stack.

The 2025 recordings show agents calling individual MCP tools. The 2026 series shows the layers underneath and around them: GPU offload in CLIO Core, deployment on national systems, memory that persists across sessions, and agents working inside DOE laboratory projects.

See the platform

Try the system

From a demo
to your dataset.