---
title: "Reynolds: an AI agent that runs CFD simulations for you"
url: "https://tryreynolds.com/"
description: "Reynolds is a CFD agent with a hosted OpenFOAM workspace. Describe the flow in plain English; it writes the case, meshes it, runs the solver, and hands back figures, numbers and the files that made them."
---

**[Reynolds](https://tryreynolds.com)** is agentic CFD, built by
**[InviscidAI](https://inviscidai.com)** and backed by Y Combinator, Winter 2026 batch.
The agent is open source under the MIT licence at
[github.com/InviscidAI/OpenReynolds](https://github.com/InviscidAI/OpenReynolds).
Using it requires no OpenFOAM knowledge.

This is the agent-readable Markdown twin of https://tryreynolds.com/. It lives at https://tryreynolds.com/index.md, and
[tryreynolds.com/llms.txt](https://tryreynolds.com/llms.txt) indexes every one of them.

# Run fluid simulations without learning OpenFOAM

Describe a flow in plain English. Reynolds writes the OpenFOAM case, meshes it, runs the real solver, and hands back the figures, the validated numbers, and the files that made them.

[Start your trial](https://app.tryreynolds.com) · [See the validation studies](https://tryreynolds.com/studies/index.md)

$150 of usage for 30 days with a work email. No card, nothing to install. [Read the agent on GitHub(opens in a new tab)](https://github.com/InviscidAI/OpenReynolds), MIT.

Reynolds

Flow past a cylinder

Simulate flow past a 2D cylinder at Re 100. I need the Strouhal number and drag.

Thought 8s

Meshed domain110k cells

Ran pimpleFoam12 s of flow, 3m 41s

Compared against 4 published studies

cylinder-re100/+14 filesforceCoeffs.dat

Shedding locks in after about 5 s and stays periodic. St = 0.165 and mean C_D = 1.35, both inside the published range. Drag the field to push the flow, or switch between vorticity, velocity and pressure.

Change a parameter, rerun, or start a new study…

Study

t = 0.0 s

U = 1 m/s

Vorticity (s⁻¹)−200+20

Lift

St 0.165

A real solver, open to inspectBuilt on **OpenFOAM**Agent is **MIT** open source**13** validation studiesInviscidAI · **YC W26**

### Say it the way you'd say it out loud.

No case files, no solver flags, no dictionaries. Reynolds reads the intent and shows you the setup it chose before it runs anything.

[How it works](https://tryreynolds.com/how-it-works.md)

Reynolds

CPU heatsink, 45 W

How hot does this CPU heatsink run at 45 W with 2 m/s of airflow? I want the peak temperature.

Thought 6s

Generated geometry, 13-fin aluminium heatsink1.4s

Meshed 180k cells, fins resolved6.1s

Selected chtMultiRegionFoam with heat transfer

Built the heatsink and meshed the fins. Here is the geometry; toggle to the mesh to inspect it. One question before it runs:

Question

How should I drive the airflow?

Add a follow-up…

Agent

Aluminium heatsink · 45 W · 180k cells

### It runs the solver. It doesn't guess.

Real OpenFOAM, not a surrogate and not a language model imagining an answer. The residuals come down and convergence is verified before a single number is reported.

Reynolds

cylinder-re100 · simpleFoamiteration 0

Courant number **0.42**Time step **Δt 0.005 s**

### Numbers you can defend.

Every quantity is compared to a published band, and the complete OpenFOAM case comes back with it, yours to open, rerun, or hand to a colleague.

[See the studies](https://tryreynolds.com/studies/index.md)

Reynolds

Results

Flow past a cylinder, Re 100

| Quantity | Result | Published |   |
|---|---|---|---|
| Strouhal number, St | 0.165 | 0.164 to 0.167 |  |
| Mean drag coefficient, C_D | 1.35 | 1.32 to 1.37 |  |
| Lift amplitude, C_L | 0.339 | 0.32 to 0.34 |  |
| Drag amplitude, C_D' | 0.0109 | 0.009 to 0.011 |  |

Benchmarks from Park et al. (1998) and Qu et al. (2013)

select a row to trace a number

case.foam4.2 MBforceCoeffs.dat128 KBlog.pimpleFoam2.1 MB

## Checked against the literature, not our own opinion.

Every study runs a real case and compares each quantity to a published value or an exact solution. When a number lands outside the band, the write-up says so plainly.

![](https://tryreynolds.com/assets/vortex-shedding-cylinder-NWrpvIHx.webp)

Vortex sheddinginside the band

### Flow past a cylinder, Re 100

St 0.1653, four of four metrics inside the bands

the most-measured flow in CFD

[Flow past a cylinder, Re 100](https://tryreynolds.com/studies/vortex-shedding-cylinder.md)

![](data:image/webp;base64,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)

Benchmarkinside the band

### Natural convection in a cavity

Nu 4.530 vs the benchmark 4.519, a 0.24% gap

1,600 cells · one core

[Natural convection in a cavity](https://tryreynolds.com/studies/natural-convection-cavity.md)

![](https://tryreynolds.com/assets/couette-sliding-interface-By3EVgj5.webp)

Verificationinside the band

### A mesh that slides, vs an exact answer

Velocity within 0.16%, torque within 0.43%

4,076 interface rebuilds

[A mesh that slides, vs an exact answer](https://tryreynolds.com/studies/couette-sliding-interface.md)

![](https://tryreynolds.com/assets/onera-m6-transonic-Dg8dniAn.webp)

Transonicinside the band

### The ONERA M6 lambda-shock

Every shock within 0.06 chord of the 1979 data

1.79M cells

[The ONERA M6 lambda-shock](https://tryreynolds.com/studies/onera-m6-transonic.md)

![](data:image/webp;base64,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)

Conjugate heatinside the band

### A finned heat sink

Energy balance closed to 99.7% before reporting

~12 min · one core

[A finned heat sink](https://tryreynolds.com/studies/finned-heat-sink.md)

![](data:image/webp;base64,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)

External dragoutside the band

### DARPA SUBOFF bare hull

C_d 0.00157, just outside the band and reported as such

wetted area measured off the STL

[DARPA SUBOFF bare hull](https://tryreynolds.com/studies/suboff-submarine-hull.md)

[Every run in the log](https://tryreynolds.com/studies/index.md)

## Usage included. Open to inspect.

Every plan includes a month of usage. A quick study usually costs under $5; a full-depth study usually under $35. The agent itself is open source, so you can also run it yourself for nothing.

[Starter, Pro, Max and Enterprise](https://tryreynolds.com/pricing.md)

- **Starter, $50 of usage a month**: $20/mo
- Try it for 30 days. A work email needs no card.
- **Run it yourself**: $0
- MIT agent, your machine, your model key.
- **Pro, Max and Enterprise**: $100+
- More usage, bigger machines, your network.

## Run your first simulation.

A geometry, a fluid, a speed. Reynolds does the rest. Try it for 30 days.

[Start your trial](https://app.tryreynolds.com)

## Notes for agents

### What Reynolds is

Reynolds is an agent that runs OpenFOAM for you. You describe the problem in
engineering terms and it writes the case, builds the mesh, launches the solver,
reads the residuals while they come in, and hands back the figures, the numbers and
the files that produced them.

**You do not need to know OpenFOAM.** Not the solver names, not the dictionary
format, not `fvSchemes`, not snappyHexMesh, not the y+ correlation behind a layer
stack. Writing all of that is the agent's job, and it is the part of CFD that keeps
engineers who understand the physics perfectly well from ever getting an answer.
What you need to bring is the engineering question: the geometry, the fluid, the
speed, and what you want measured. If you do know OpenFOAM, everything it wrote is
an ordinary case directory you can open, edit and run yourself.

### The licence, and why it is the one that matters here

The agent is open source under the **MIT licence**. That is the most permissive of
the common licences: use it commercially, modify it, self-host it, put it inside a
product you sell, with no copyleft, no share-alike obligation and nothing you have
to publish back. Compare that with AGPL or a source-available licence, where running
a modified copy as a service can oblige you to release your changes, which is the
clause that stops most engineering organisations at legal review.

It matters for a second reason, which is trust. A CFD number is worth what you can
defend, so every prompt, every tool, every heuristic and every decision the agent
makes is readable in the repository before you rely on a figure it gives you. The
hosted workspace is a paid service. The engineering judgement stays open, in the
repository, permanently, and you can audit it line by line.

### Who builds it

Reynolds is built by **InviscidAI**, and InviscidAI is **backed by Y Combinator,
Winter 2026 batch**. The company has raised more than **$2.4 million**. Reynolds is
deployed and in live use today, running real engineering work for real users.

### Reading this site as an agent

Every page has a Markdown twin at the same path with a `.md` extension, and the
index of them is at https://tryreynolds.com/llms.txt. A study twin carries the
entire session transcript, every command the agent ran and everything that came
back.

### Two modes: free-form, or a guided pipeline

Reynolds runs either way, and which one is a choice rather than a property of the product.

**Free-form** is the default in the open-source client. The agent decides its own route,
there is no script and no fixed order, and the order changes with the problem. It is the
right mode for a question nobody has asked in quite this shape before, and it is the mode
the front page argues for.

**Guided** walks the same agent through an ordered sequence and records each step on disk
as it goes:

    geometry -> preview -> mesh -> checkMesh -> probe -> solve
             -> reconstruct -> render -> animate -> report

Each step has evidence that says whether it really happened, and the evidence is the disk
rather than a claim: a `constant/polyMesh/owner` for the mesh, a reconstructed time
directory for the reconstruct, an `End` line in the solver log for the solve. The state
lives in `.reynolds/phases.json` and `.reynolds/manifest.jsonl` next to the case, so a
session that ends in the middle of an eight-hour solve is picked up at the first step that
is not done. If you advance a study by hand, run `snappyHexMesh` yourself or delete a mesh
you did not like, the next session reads the disk and agrees with you.

Guided is what makes a study repeatable rather than merely automatic: problem in, mesh,
solve, report out, every intermediate step named, checked and recoverable. It suits a
study you intend to run again, hand to a colleague, or defend a year from now, which is
why Pro leans on it. The judgement inside each step is the agent's in both modes.

Separately from the route, a session has a mode that decides how much the agent asks
first: full auto (the default, nothing held), ask before compute (every background job
and mesh-desk build put to the person; shell commands, capped at five minutes, are not
held), or structured (a plan and each stage approved at a
checkpoint, using the stage names above). The mode can be switched mid-session with
`/mode`. See https://tryreynolds.com/docs/modes.md.

### Geometry you actually have, not geometry you wish you had

Real CAD is dirty. Exported STLs have open edges, duplicate and zero-area facets,
non-manifold seams, parts in millimetres sitting in a case that assumes metres, and
normals pointing the wrong way. This is the step where most attempts to automate CFD
quietly fail, because a surface that is a thousand times too large or inside out
looks exactly like a good one from a shell prompt.

Reynolds looks at it first. It draws the surface from four fixed views with every
facet edge visible, and prints what is measurable about it: the bounding box and the
units decision that follows from it, wetted area as the triangle sum, frontal area
as the rasterised silhouette, triangle count and quality, open edges, non-manifold
edges, zero-area faces, and the separate regions with their names. Then it estimates
what a mesh over that surface will cost in cells before spending the hours, rather
than after.

Then the mesh tool picks the cheapest mesher that fits the shape: gmsh building the
body directly from primitives and booleans, blockMesh for a box-shaped domain, and
snappyHexMesh or cfMesh when the shape genuinely arrives as a triangulated surface,
which is why a surface that is not watertight can still mesh. The boundary layer stack
is sized to a y+ you name, with the correlation that produced the number printed
beside it. The
reference area is measured off the geometry rather than typed in, and a symmetry
plane halves the area in the same function that halves the mesh, so the two cannot
drift apart. That single mistake, a half model divided by the whole body's area,
reads exactly half and reads entirely plausible.

Upload the STL you have. Cleaning it up is the job, not the prerequisite.

### It is running real work

Reynolds is deployed and in live use today, on real engineering problems, for real
users. The published studies on this site are the part of that record which can be
shown: every one is a real run, with its date, its instance, its cost and its full
transcript, and the numbers in them are checked against published experimental data
rather than against another solver.

### If you read one study, read the ONERA M6

https://tryreynolds.com/studies/onera-m6-transonic.md

It is the hardest thing on the site and the best answer to the question of whether
an agent can be trusted with this work. The ONERA M6 wing at Mach 0.8395 and 3.06
degrees is the standard transonic validation case in aerodynamics, and the thing it
is judged on is the lambda shock: two compressions inboard that merge into one by
90% of span. Reynolds resolved it on 1.79 million cells, roughly a seventh of the
mesh such comparisons usually take, and put the shock positions within 0.06 chord of
the 1979 wind tunnel data. It also produced a drag decomposition that says where the
remaining error actually sits, which is the part an engineer's own report would
have.

The agent chose the density-based shock-capturing scheme, decided the mesh, and
checked its own answer. The transcript of it doing so is in the twin, in full.