Quickstart: web app

Create a project in the web app, understand its files, run it, and see the result on the dashboard.

Before you start

You'll need a Harumi account and access to the platform. Don't have one yet? See Creating an account first.

First time in Harumi?

After your profile, the welcome step asks what you want to improve. Describe the problem in your own words and Harumi creates the project and starts its checklist for you. See Creating an account. This guide is for creating a project yourself, from starter files.

This guide walks the web app path for journey 1 of Starting a project — nothing yet, starting from scratch. Adopting existing code, or working from a terminal instead of the browser? See Starting a project for those paths.

Create a project

From your projects home, click New project and choose whether it belongs to your personal workspace or an organization. Harumi provisions a git repository for the project, seeded from a starter template. Advanced options in the dialog let you leave out the starter files, add a .gitignore, or start from a ZIP instead.

Look at what you got

The starter template commits four files to your new repository:

harumi.toml

main.py

overview.toml

README.md

Open the Code tab to browse them:

harumi.toml — the run manifest. It says what command Harumi runs and on which compute kernel:
```
[run]
command = "python main.py"
kernel = "or_python_small"
```

main.py — your entry point. The starter version writes a small result to output/output.json:

result = {
    "objective": 128_450,
    "rows": [
        {"name": "Item A", "value": 52_400},
        {"name": "Item B", "value": 38_900},
    ],
}

dashboard/overview.toml — declares the widgets shown on the Dashboard, bound by key to output/output.json. The starter config binds a metric to objective and a table to rows — matching what main.py writes. Each dashboard/<name>.toml is its own dashboard: add a second file and a picker appears on the Dashboard to switch between them. See Dashboard datasets, metrics, and the clock for the optional sections beyond widgets.

No notebook cells

A run is exactly the command declared in harumi.toml, executed against the code on the live branch (main). There's nothing else implicit about it.

Edit and commit

Open a file in the Code tab, switch to Edit, make a change, and click Commit changes with a commit message. This writes directly to main — there's no separate save/publish step.

For anything beyond quick edits (working in your own editor with git), see Working with the repository or use the CLI to git push from your machine. To add a data file without committing it, use the Data Sources tab's Files section instead — it's not tracked in git, and appears at inputs/ inside every run.

Run it

Click Run in the toolbar. Harumi clones the repository at the current commit and executes the harumi.toml command on the configured kernel.

See the result

Back on the Dashboard, View latest output shows a live terminal with stdout/stderr while the run is in progress. Once it finishes, the widgets declared in dashboard/overview.toml render using the JSON your run wrote — so the starter project shows a real metric and table on its very first run.

Next: change the kernel or the model

To use a larger kernel or a licensed Gurobi image, edit the kernel value in harumi.toml:

kernel = "gurobi_python_medium"

Available kernels: or_python_small, or_python_medium, or_python_large, or_python_xlarge, or a gurobi_python_* size if your organization has a Gurobi license.

To build the actual model, either write the code yourself, or open Harumi AI Chat and describe the problem — in Agent mode it can build and run a model for you. See Harumi AI Chat.