RAS Agent runs the complete HEC-RAS 2D workflow from a pour point - terrain ingestion, watershed delineation, peak flows, model build, headless model execution, GIS results export, and HAZUS flood loss estimation - and wraps it in an auditable, file-native study record where automation can advance a model but only a named engineer can accept it. Built at the Illinois State Water Survey to produce Base Level Engineering-quality 2D flood models at watershed scale.
Each stage is independently testable and produces typed result objects. Run the full pipeline or individual stages - with mock mode for testing without live data or a network connection. Validated on real geometry: the Spring Creek (Lower Sangamon, IL) pilot ran a wet HEC-RAS 2D solve (RasUnsteady 7.0.1) on Illinois Computes HPC in June 2026; in October 2026 the same watershed completed the full pipeline end-to-end (see Recent Milestones). Stage 02 also produces a HAND terrain-screening depth grid as a fast first-look baseline before the full solve. RAS Agent is open source under the Apache 2.0 License. It drives HEC-RAS, free software from the U.S. Army Corps of Engineers. Hosted beta runs execute on University of Illinois hardware; the HEC-RAS software itself is never distributed.
Built by engineers for engineers. Designed to handle the unglamorous parts of hydraulic modeling - data wrangling, format conversion, and model assembly - to amplify your expertise, not replace it.
batch.py. Resume on failure - skip completed runs automatically. Outputs a summary CSV for each batch run.
Active development - major capability unlocks in the last development cycle.
main: Spring Creek (Lower Sangamon), Money Creek, Hickory Creek, the Upper and Lower Cache River, Little Crooked Creek, and the North Fork Vermilion in Ford County. Five are validated against active USGS gauges; two against ISWS regulatory 2D models (one an effective FEMA FIS). Tier 1 runs in mock mode on every PR; Tier 2 will run full-resolution on HPC.
systematic_calibration.py composes ras-commander calibration helpers into reviewable Manning's n / SCS Curve Number parameter grid sweeps, scored by hydrograph correlation, NRMSE, and a composite goodness-of-fit ranking.
pilot_channel.py generates conservative LiDAR terrain-mod proposal packages from TauDEM centerlines - STA/ELEV profiles, cut/fill summaries, reviewer flags, and HTML report. Proposal-only: never edits production terrain. Human engineering signoff required before application.
qaqc_report.html, diagnostics, SVG maps, and a signoff.json. Production promotion is blocked until human approval is recorded.
run-hpc.sh) drives the whole flow: container Stages 1–5 produce the plan HDF, then hpc_submit rsyncs to Taiga, submits to SLURM over SSH, waits, fetches results, and verifies them. Validated end-to-end on real hardware in June 2026 — RasUnsteady 7.0.1 solved on an Illinois Computes node, results fetched and confirmed. Illinois Computes requires Duo on every new SSH connection: one interactive sign-in opens a shared connection that launches reuse for up to eight hours, so unattended cluster launches work only while that connection is live. The Atlas API auto-routes in-process on a toolchain host or delegates to the container otherwise.
golden-smoke job runs the mock pipeline end-to-end for the seven golden watersheds.
A hosted beta of RAS Agent is opening. Pick an Illinois watershed and the service builds a candidate 2D HEC-RAS model — terrain, mesh, and boundary conditions, with hosted solves following as the solve stage completes integration — checked by the same QA gates as a local build and delivered as a model package with its study record. Outputs are candidate models: a starting point for H&H work, not a finished study, and they carry that label.
Access is by approval while the beta stays small. Join the waitlist and we will email you as seats open. Already have an account? Sign in.
Hosted beta runs on University of Illinois hardware. RAS Agent is an open-source project built at the Illinois State Water Survey (CHAMP), Prairie Research Institute, University of Illinois.
RAS Agent is the regulatory-grade HEC-RAS engine in a family of open tools. Sibling projects handle fast statewide screening and probabilistic risk; FloodStack is the layer that will chain them. Development is also steering toward FEMA's Future Flood Risk Data (FFRD) direction — aligning RAS Agent's study data and metadata with the interoperability standards FFRD is setting, so studies produced here carry forward into FFRD-era workflows.
rqm-data-model is the next step.