Constellation
... placed 1st in the HPC track at TAMUHack 2026.
Constellation is an "AI-native IDE" designed specifically for HPC environments.
The goal was to replace terminal-heavy workflows that require a CS background
with a visual execution graph and an agentic AI interface.
It's implemented as a web-based IDE, where
users upload data and describe their goal in natural language,
and Constellation assists the user in constructing, executing,
and debugging parallel workflows, so they can focus on their research problems.
The way workflows are structured (and the idea in the first place) was inspired by
Citadel's internal commodities research/modeling platform.
Tasks are deployed in production clusters with AWS Batch, or run locally on the backend for
quick testing with smaller files. Scheduler scripts and batch logic are abstracted away,
allowing users to focus on workload structure rather than job syntax. The AWS EC2 workers
that handle these compute jobs are scaled dynamically to the workflow.
Input nodes can be constructed with single or multiple input files. Multiple input files are
pipelined through the program to maximize compute efficiency.
"Our goal is to make parallel computing practical for users who do not have prior
HPC
experience, without constraining the capability of our users."
The coolest part (a lil biased) was building out actual cluster deployment rather than a
simulated HPC workload,
and also building out an AI agent that made your life *less* shitty.
I built this with my friends
Cam Stone,
Athul Suresh,
and
Josh Wu.
GitHub
· Demo Video
· Hackathon · 2026