Open Net Worth
Open Net Worth is an open-source personal AI wealth assistant you run yourself: one ledger for your whole financial life, worked by an AI agent you control.
Ask the SIO assistant questions about pensions, benefits and complaints
AI summary · website content
FinanceJavaScript · CSSGitHub @Manali1344OnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
No updates detected yet. GitHub releases will appear here.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
The maker's introduction consists of the line above. Read the repository README for more details. Repository README ↗
Loading the full README.
Read the full README ↗Working demo for Bahrain Tender Board 3/2026/SIO — Chat Bot Solution, Social Insurance Organization, Kingdom of Bahrain. Built by Nanta Tech.
Needs Node 18 or newer. Nothing to install.
cp .env.example .env # add your Anthropic API key
npm start # http://localhost:3000
In VS Code you can also press F5 — the launch config starts the server and opens the browser.
The key stays in .env on the server side; the browser calls /api/chat and never sees it.
No speech key is needed. Read-aloud uses the browser's own voice when one is installed for the
language (Edge has natural Arabic voices); otherwise the server fetches free audio through
/api/tts, so Arabic also plays in Chrome, Firefox and Safari. Speech input uses the browser's
built-in recognition in Chrome, Edge and Safari, and in Firefox runs Whisper inside the page
(a one-time ~75 MB model download). Both need internet access. The free read-aloud source is
unofficial — the delivery build should use a contracted speech service.
Roughly four minutes, and it lights all eight items on the coverage rail:
Reset demo data in the bottom-left restores the starting state between demos.
server.js Node server + Anthropic proxy (no dependencies)
public/index.html Markup
public/styles.css Styling
public/app.js Chat engine, rule engine, KB, logs, dashboard
CLAUDE.md Context for Claude Code
.env.example Copy to .env
Integration with SIO core systems, SSO, production security hardening, hosting and Bahrainisation compliance are addressed in the technical bid. The demo states this on screen rather than implying coverage it does not have.