Maniac Lab

AI and Facilities for Frontier Science

Trustworthy agentic systems acting on and through the cyberinfrastructure of large experiments. Earned autonomy for operations; one credential-brokered gateway for physicists.

AI-generated illustration
One Conversation, the Whole Analysis

Elwood lets an analyzer describe the physics while agents run the loop, from dataset discovery through HTCondor to the fit, grounded in facility context and gated by humans.

AI-generated illustration
Cyberinfrastructure for the Large Hadron Collider

We lead the ATLAS Midwest Tier2 Center, more than 40,000 CPU cores and 25 PB on the Worldwide LHC Computing Grid, and operate the Analysis Facility at UChicago for U.S. ATLAS physicists.
High-Throughput Computing for KOTO

We connect the University of Chicago KOTO group, led by Yau Wah, to the Open Science Pool and to campus storage for the search for an ultra-rare neutral kaon decay at J-PARC.

Photo KOTO collaboration, J-PARC
Analysis Computing for SBND

The Pile cluster serves University of Chicago physicists on the Short-Baseline Near Detector at Fermilab, with HTCondor batch, login nodes and a Globus data transfer endpoint on Kubernetes.
Computing for the South Pole Telescope

MANIAC Lab operates cyberinfrastructure for the South Pole Telescope at the Pole and in Chicago, supporting SPT-3G data processing and analysis.
A Global Data Network for XENON

MANIAC Lab operates the Rucio global data management service for the XENON dark matter experiment at Gran Sasso, Italy.

Hero

AI and Facilities for Frontier Science

We build and operate the cyberinfrastructure behind the largest scientific instruments, and we are making it a place where AI agents can work, trusted to help run the facility and able to carry a physicist's analysis from question to result.

Nicholas Metropolis with the MANIAC III computer at the University of Chicago, 1960s

Our (admittedly frivolous) name is a nod to the University of Chicago’s first computer, MANIAC III. Built in 1961 at the Institute for Computer Research, MANIAC III, short for Mathematical Analyzer, Numerical Integrator, and Computer (Model III), was a second-generation machine that replaced vacuum tubes with solid-state components. It was developed under the leadership of Nicholas Metropolis (SB 1937, PhD 1941), who carried forward and extended computer designs he had helped build at Los Alamos after World War II.

How We Work

Models and runtimes change by the month. The facility layer, its context, identity, trust and packaging, is ours to own, and it is where agents become useful and safe.

The facility layer

We run the Analysis Facility at UChicago, the Midwest Tier2 Center and the RP1 research platform, and host the IRIS-HEP Scalable Systems Laboratory. We write the facility down once, its storage, schedulers, data and identity, so every agent inherits it.

Facilities and platforms →

AI acting on the facility

Shannon governs agents that help operate the infrastructure. A trust ladder from observe to operate, promotion by evaluation, runbooks and policies reviewed as pull requests. AI proposes, experts decide.

Governance and operations agents →

AI acting through the facility

Physicists plug their own agents into one credential-brokered MCP gateway. Agents speak intent, not backends, so playbooks port across facilities, and a shared marketplace carries the know-how.

Gateway, playbooks, marketplace →

Collaborating with the MANIAC Lab

We work with researchers and scientific collaborations at every scale and at any institution.

Contact Us

AI and Facilities for Frontier Science

One Conversation, the Whole Analysis

Cyberinfrastructure for the Large Hadron Collider

High-Throughput Computing for KOTO

Analysis Computing for SBND

Computing for the South Pole Telescope

A Global Data Network for XENON

AI and Facilities for Frontier Science

How We Work

The facility layer

AI acting on the facility

AI acting through the facility

Collaborating with the MANIAC Lab