Skip to main content

Open Net Worth

Open Net Worth

Agent harness for personal finance

Website · Download · Docs · Live demo · Discord

Latest release License: AGPL-3.0 Documentation Discord

Watch the three-minute product demo
▶ 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.

Chatbot bolted onto an app An agent harness
What the AI touches a summary of your data the ledger itself, through real write tools
When it's wrong you find out later a confirm card shows the change before it lands
What it can do answer act, on a schedule, unattended if you allow it
Extending it wait for the vendor connect an MCP server and it gains tools

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.

What's inside

Ledger Every account you own or owe, in any currency: banks, cards, loans, investments, retirement. Transfers, splits, reconcile, and statement import with a review step before anything books.
Budget Zero-based envelopes (Ready to Assign, targets, credit card payments) or a simple 50/30/20 split, plus a cash flow projection.
Investments Holdings, buys, sales, dividends, lots and realized gains, options, RSU and other equity grants, watchlists and price alerts.
Planning Big dated commitments and how each is funded, and a retirement outlook: the odds your money lasts and the age you could retire.
Lucius The AI agent on every screen. He works your real book through real tools: logs and sorts transactions, reconciles accounts, builds reports. Connect an MCP server and he acts in other apps too, like placing a trade with your broker. You choose what he does on his own and what he asks you first.
Automations Jobs Lucius runs on a schedule or when something happens: a daily briefing, a weekly report, a bank sync, logging purchases from email.
Skills and memory Saved playbooks he follows for a job (built in, or your own), and facts he remembers about you between conversations.
Connectors Bank and broker sync (SimpleFIN, Plaid, Enable Banking, Lunch Flow, Alpaca, Interactive Brokers), YNAB, Lunch Money, your mailbox, Telegram, web search, and any MCP server.
Your AI An API key (Anthropic, OpenAI or any OpenAI-compatible endpoint, including a local model), or the Claude Code, Codex or Antigravity sign-in you already have. Other AI apps can use your book too, through onw mcp.

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

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

Platform Download Terminal install
macOS (Apple Silicon; signed and notarized DMG) opennetworth.ai/download/mac curl -fsSL https://opennetworth.ai/install.sh | sh
Windows 10/11 x64 (installer) opennetworth.ai/download/windows irm https://opennetworth.ai/install.ps1 | iex (PowerShell)
Linux x86_64 (AppImage, or .deb from the releases page) opennetworth.ai/download/linux curl -fsSL https://opennetworth.ai/install.sh | sh

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):

Command What it does
onw start --background Run it without keeping this terminal, until onw stop or a reboot
onw stop Stop it
onw restart Restart it, the way it was running
onw status Show whether it's running, its URL, version and folder
onw logs Show the end of its log. -f keeps following it
onw upgrade Update to the newest release
onw reset-password Set a new password if you've forgotten it
onw version Print the installed version

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 http://localhost:8080 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.

    What that installs, if you'd rather see it or do it by hand

    The service runs the same interpreter onw runs on, so it is identical for a uv install and a checkout's .venv; it also carries your shell's PATH (launchd and systemd give a fresh process a minimal one) and any of HOST, PORT, ONW_ROOT, DATA_DIR, CACHE_DIR, LOGS_DIR, UV_TOOL_DIR, UV_TOOL_BIN_DIR, UV_CACHE_DIR, UV_PYTHON_INSTALL_DIR, XDG_DATA_HOME that were set when you installed it.

    macOS (~/Library/LaunchAgents/ai.opennetworth.app.plist):

    <?xml version="1.0" encoding="UTF-8"?>
    <!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
    <plist version="1.0"><dict>
      <key>Label</key><string>ai.opennetworth.app</string>
      <key>ProgramArguments</key>
      <array>
        <string>/path/to/python3</string>
        <string>-m</string><string>backend.cli</string><string>start</string>
      </array>
      <key>WorkingDirectory</key><string>/Users/you/.open-net-worth</string>
      <key>RunAtLoad</key><true/>
      <key>KeepAlive</key><true/>
    </dict></plist>
    

    Linux (~/.config/systemd/user/open-net-worth.service):

    [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
    

    See backend/cli/autostart.py for the exact commands (launchctl bootstrap / systemctl --user enable --now).

  • 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.

Metadata

Release files for open-net-worth 0.1.43

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for open-net-worth 0.1.43
File Size Uploaded Provenance Actions
open_net_worth-0.1.43.tar.gz 14.8 MB With provenance Details for open_net_worth-0.1.43.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for open-net-worth 0.1.43
File Interpreter ABI Platform Actions
open_net_worth-0.1.43-py3-none-any.whl Python 3 none any Details for open_net_worth-0.1.43-py3-none-any.whl

Total release size: 30.7 MB

Release files / open_net_worth-0.1.43.tar.gz

Download URL open_net_worth-0.1.43.tar.gz
Size 14.8 MB
Tags Source
SHA-256 checksum
How to use checksums
92eadc8b4f74144dc5ad6223bce9bb99227b8f41fc859b48c0eb9fef422d55b6
BLAKE2b-256 checksum
How to use checksums
41f93c0dc254fdb59856ca568d906dac487b8c6666ed86043250cc87d30170be
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 8, 2026.

Transparency log

Release files / open_net_worth-0.1.43-py3-none-any.whl

Download URL open_net_worth-0.1.43-py3-none-any.whl
Size 15.9 MB
Tags Python 3
SHA-256 checksum
How to use checksums
98f04a352f48d8e9cdb22f9a58e311eb72a3f0a776c3b32b15b04e903e7424bb
BLAKE2b-256 checksum
How to use checksums
5bf7f835c883712bec0578f0596abba4008dc201e2889b5e4f2b057f32de9ee4
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 8, 2026.

Transparency log

Security for open-net-worth 0.1.43

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for open_net_worth-0.1.43.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 8, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.43 This release

2 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page