Open Net Worth

Agent harness for personal finance

Website · Download · Docs · Live demo · Discord

_{If this is useful, a star helps others find it.}

_{▶ Watch}

An open-source agent harness for personal finance. A real multi-currency ledger, budgets, and investments — plus an AI that can actually read and change them, not just talk about them. Self-hosted, on a machine you control.

Most personal-finance apps that added AI let it describe your data. Open Net Worth is built the other way round: the ledger, the budget, and the investment book are the substrate, and the assistant (Lucius) is an agent operating them through a registry of real tools — the same guarded write paths the UI uses.

Every tool carries a permission level — always_allow, needs_approval (the default), or blocked — enforced at dispatch for every tool in the app.

Nothing leaves your machine except the calls you explicitly configure (an AI provider, a price feed, an optional connector), and there is no telemetry. The one exception is a problem report you choose to send: you read it first, and it goes only when you press Send.

Compared with Claude and ChatGPT Personal Finance

_{Based on each launch's announcement and coverage as of November 2026.}

The open-source alternative to Monarch, YNAB, Actual Budget, Firefly III and Ghostfolio

Monarch Money and YNAB keep your budget on their servers. Actual Budget and Firefly III keep it on yours, and Ghostfolio does the same for a portfolio. Open Net Worth puts the budget, the holdings, the loans and the property in one book on your own machine, and gives an AI agent the tools to keep that book. If you searched for an open-source Monarch Money alternative, a YNAB alternative you can self-host, or a Ghostfolio alternative that also budgets, this is the repository.

Each post also says where the other tool is the better pick. Monarch and YNAB have phone apps and household sharing, Actual Budget is the more established budget, and Ghostfolio is the more focused portfolio tracker. All of them side by side: Open source net worth trackers compared.

What's inside

Is this for you?

Yes, if you want to self-host your own finances, you're comfortable running a small app on your own machine or a server you control, and you'd rather have an AI agent do the work (categorize a transaction, reconcile an account, explain a swing in net worth, act in the apps you connect) than just chat about screenshots of it.

Not yet, if you need a polished, install-and-forget consumer product, multi-user or family accounts, or mobile apps.

Requirements

• The desktop app: macOS on Apple Silicon, Windows 10/11 (x64), or Linux (x86_64, AppImage or .deb). It bundles its own Python, so nothing else needs installing. Intel Macs and arm64 Linux have no desktop build yet; what differs on Windows is listed in docs/WINDOWS.md.
• Running a server from source: Python 3.12+ and Node.js 22+ (macOS, Linux or Windows).
• An AI model — first run asks for one, with no skip: an API key (Anthropic, OpenAI, or any OpenAI-compatible endpoint), an existing Claude Code, Codex or Antigravity CLI sign-in on the same machine (detected for you), or a free local model through Ollama.

Getting started

Option A — the desktop app (recommended)

Download it from opennetworth.ai, or from the public releases page:

The Windows installer is not code-signed yet, so SmartScreen may show a warning: choose More info → Run anyway. install.ps1 verifies the download against the release's SHA256SUMS; add -RequireSigned to refuse an unsigned installer. install.sh verifies the same checksum before it installs anything. The macOS and Windows apps update themselves in place; a Linux AppImage replaces itself after checking its SHA-256, and a .deb points you to the releases page.

Then follow the first-run screen: it asks where your book lives (a local folder, or an existing server), creates your login, picks a base currency, and hands off to Lucius to add your first account. Your data defaults to ~/.open-net-worth/, outside the app, so updating or reinstalling never touches it. See the desktop guide for background mode, start at login, watched folders and keyboard shortcuts.

Option B — a server

1. Install it. You don't need Python or Node.js on your system. This is for macOS and Linux; on Windows, follow these steps instead.

curl -fsSL https://github.com/open-net-worth-ai/open-net-worth-releases/releases/latest/download/install-server.sh | sh

If it says onw was added to your PATH, run the source line it shows (for zsh, source ~/.zshenv) or open a new terminal. It finishes by listing the commands you're likely to need next.

2. Start it. Your browser opens the app, and first run takes it from there.

onw start --open

3. Optional: keep it running and up to date. Press Ctrl+C to stop the copy from step 2, then run the command below. It starts the app at login, restarts it after a crash and installs each new signed release. Leave out --auto-upgrade to update by hand. See Keeping it running.

onw start --autostart --auto-upgrade

Other commands you may need (full list):

Good to know:

• Your data lives in one working folder, ~/.open-net-worth/, holding data/, cache/, logs/ and backups/. First run lets you put it elsewhere and remembers the choice. No .env file is needed.
• The desktop app can connect to a server like this instead of using a local book.
• Other AI apps like Claude Desktop, Cursor or ChatGPT can use your book while the server is running. See Use your book from other AI apps.
• Working on the code? Run make setup start from a checkout (Python 3.12+ and Node.js 22+).

Option C — Docker

1. Download the Compose file into an empty folder.

curl -fsSLO https://github.com/open-net-worth-ai/open-net-worth-releases/releases/latest/download/docker-compose.yml

2. Pick a password and start it. Use at least 8 characters. Compose won't start without a password.

AUTH_PASSWORD='pick a password' docker compose up -d

In Windows PowerShell, use curl.exe in step 1, and run this in step 2:

$env:AUTH_PASSWORD='pick a password'; docker compose up -d

**3. Open ** and log in with that password.

Good to know:

• Why the password is required: your browser reaches the container from Docker's bridge, not from localhost, so the "same machine, no login" shortcut never applies. Without a password, nothing could operate the instance. Details are in the first-run guide.
• Your data lives in a named volume that survives docker compose down. Migrations run at boot.
• The version is the public image ghcr.io/open-net-worth-ai/open-net-worth, pinned by that Compose file to the release it came with. ONW_VERSION=x.y.z runs another.
• Working on the code? From a checkout, add -f compose.build.yml --build to build the image locally.

Coming from YNAB or Lunch Money?

Add the YNAB or Lunch Money connector with a personal access token and your transactions flow in, refreshed every 6 hours. Categories and budgets are not copied: set them up here, or let Lucius or an Automation categorize as transactions arrive. The budget works the way YNAB's does (every dollar assigned, Ready to Assign, envelopes that hold their overspend until month end). Steps: Bank and brokerage connectors.

Keeping it running

The desktop app does this itself: Settings → Desktop has Keep running in the background and Start at login. For a server, Open Net Worth is one Python process (onw start, which runs uvicorn and serves both the API and the built frontend on the same port) — there is no separate web server (no Apache, no nginx) in front of it, and none is required.

• Docker already restarts itself: docker-compose.yml sets restart: unless-stopped, which covers a crash and a host reboot, as long as the Docker daemon itself starts on boot (the default on Docker Desktop and most Linux installs).

• Not using Docker? One command installs it as a boot service, so it starts at login/boot and restarts on crash, with no terminal window to keep open:

  onw start --autostart
  

  (onw autostart on is the same thing, and onw autostart off turns it off again. From a source checkout, make autostart runs setup first, then the same thing.) This installs a per-user launchd LaunchAgent on macOS, a per-user systemd unit (plus loginctl enable-linger, so it starts even before you log in) on Linux, or a per-user Task Scheduler task on Windows — no sudo or admin needed on any of them. onw autostart on its own shows whether it's on; onw autostart off stops it and removes the service. Logs land in ~/.open-net-worth/logs/app.log.

  Labelai.opennetworth.app
  ProgramArguments

    /path/to/python3
    -mbackend.clistart

  WorkingDirectory/Users/you/.open-net-worth
  RunAtLoad
  KeepAlive

[Unit]
Description=Open Net Worth
After=network.target

[Service]
WorkingDirectory=/home/you/.open-net-worth
ExecStart=/path/to/python3 -m backend.cli start
Restart=on-failure

[Install]
WantedBy=default.target

• Updating. The desktop app updates itself (see the desktop guide); re-running its installer also works. A server installed with uv: onw upgrade by hand, which a running server installs and restarts into once it's idle, or start it with onw start --autostart --auto-upgrade to do that for each new signed release — off unless you ask for it (Upgrading). For Docker, download the new release's docker-compose.yml (it pins the image version) or set ONW_VERSION=x.y.z, then docker compose up -d (a checkout: git pull && make setup). Your data is outside all of them, and migrations run at the next start.

Configuration

Everything needed to run the app is an optional environment variable — see .env.example for the full list (working folder, host/port, CORS).

Everything needed to make it useful is configured inside the running app and stored there: the AI provider and model under Settings, and banks, brokers, email, Telegram, web search and price sources under Connectors. You never hand-edit a config file for those.

Set ONW_ROOT only to pin the working folder from outside the app: a container, or a second instance on the same machine (which also needs its own PORT).

Your data

One working folder (default ~/.open-net-worth/): a single SQLite database plus a small set of file-backed stores, alongside cache/, logs/ and backups/. It never leaves your machine except for calls you configured yourself.

Settings → Data gives you a one-click full backup .zip, automatic daily backups, and restore-from-backup — a checkpoint is saved first, so a restore is itself undoable.

Running it beyond localhost

Open Net Worth is built for one operator on a machine you control. Treat it like a self-hosted password manager, not a public web app.

• The local machine is trusted by default. With AUTH_TRUST_LOOPBACK=true (the default), any process on the same machine can call the API without a password — so the person sitting at the machine never has to log in. Set it to false on a shared machine.
• A password only gates non-localhost requests. It is not, by itself, what stands between your data and the network.
• Behind a reverse proxy, loopback trust stops working as intended. A same-host proxy (nginx, Caddy, a tunnel) makes every remote request arrive from 127.0.0.1, so it is trusted. Set AUTH_TRUST_LOOPBACK=false before putting this behind one.
• Before exposing it anywhere — a LAN, a tunnel, a public domain — set a strong password (Settings → Security), turn off loopback trust, and put it behind HTTPS. The app does not terminate TLS itself.

Found a vulnerability? See SECURITY.md — please do not open a public issue.

Documentation

• docs.opennetworth.ai — the full user guide. The same docs are built into the app, searchable, under /help.
• docs/DATA_MODEL.md — stores, fields, and how the money math works.
• CLAUDE.md — the codebase map, if you are reading code rather than using the app.
• CONTRIBUTING.md — dev setup, the dependency rule, test policy.

Stack

• Backend — Python 3.12, FastAPI, SQLAlchemy + Alembic (SQLite by default, Postgres supported)
• Frontend — React 19, TypeScript, Vite
• AI — Anthropic Claude by default, or any OpenAI-compatible endpoint; your key
• Prices — Yahoo Finance, CoinGecko

License

AGPL-3.0 — see LICENSE. Third-party dependency licenses are in NOTICE.