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.
Free accounting software for Windows, Mac, and Linux. Payroll, inventory, unlimited invoicing, multi-user Server Edition built into the signed installer (no Docker required). No cloud, no subscription
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.
Organization repository · verify with a repository file
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.
AI-Powered Stock Intelligence Through Adversarial Multi-Agent Debate
Institutional-grade quant engine + PARA-DEBATE multi-agent system + live voice analysts. US + India. 100% live data.
This codebase is available for acquisition. Contact the author for details.
Live at neuralquant.co · API neuralquant.onrender.com (v4.1.3)
Current Status — September 2026
Production live. API v4.1.3, ~950 stocks in the score cache (≈450 US + ≈500 India), nightly refresh healthy. Last full prod smoke (2026-08-18): 15/15 endpoints PASS, zero JS console errors across the app.
Recently shipped (Sessions 90–109):
Branding unified to NeuralQuant; landing, methodology, pricing refreshed.
Voice analysts live — QuantAstra (on-demand) + Veronica (page-aware companion with "Hey Veronica" wake word + morning briefing), via a LiveKit worker. TTS migrated from ElevenLabs to LiveKit Inference (cartesia/sonic-3.5).
Hermes — autonomous self-improving trading agent surfaced at /hermes (live "Matrix" dashboard, SSE log stream). Migrated from expired Railway trial to a GCP Always Free e2-micro VM.
India data parity — QuantFactor universe expanded from ~60 to ~500 NSE names via a daily-refreshed sheet sync. Legacy anjali_enrichment collapsed onto quantfactor_universe.
Security hardening (P0–P6) — Supabase RLS, log redaction, gitleaks + dependency scanning in CI, IDOR fixes, HTTP security headers + CSP (report-only), per-IP abuse limiting, webhook-signature enforcement, a security-event audit log, and an incident-response runbook. See Security.
Score-scale bug family fixed — composite_score normalization that broke trade Kelly sizing, meta scores, and backtest hit rate.
GCP India price feeder — Render's outbound IPs are blocked by Yahoo, so a self-contained feeder on the GCP VM now fetches Indian prices and writes them to stock_snapshot.
Screener — market=BOTH/GLOBAL merges US + IN; empty/500 bugs fixed.
QA pass — fixed false "loss-making" badge, CSP console error, "Sign In while authenticated" nav bug, null change_pct, broken SSE stream, empty stock_snapshot cold-start; removed the unused /alerts page and all email functionality.
Mobile — hamburger nav + bottom tab bar + responsive cards/charts/tables across the app; tightened cramped score grids on phones (verified live at 390px).
Operator follow-ups (not code): manual-deploy quantastra-agent Render worker if not yet deployed, final deletion of any remaining Railway account. The GCP India price feeder is now functional. Before any live demo, run python scripts/warmup.py (~3–5 min prior) — first-hit Ask Morgan / PARA-DEBATE is ~50s / ~85s of inherent multi-agent LLM time, and warming the exact demo tickers makes the audience-facing clicks fast.
Acquisition Overview
AI-powered stock intelligence platform — India + US.
Multi-agent Claude-powered research engine (PARA-DEBATE) · QuantFactor quintile engine + proprietary IRS% score across ~950 stocks · web + mobile (Expo) + voice (LiveKit) + an autonomous trading agent on one FastAPI backend · Anthropic Claude with an AWS Bedrock path. See neuralquant.co/methodology for the research approach.
18+ months of build. 90+ documented sessions.
Evaluate in 15 minutes — zero API keys
git clone <repo> && cd NeuralQuant
cp .env.example .env # DEMO_MODE=true is the docker-compose default
docker compose up --build
# → http://localhost:3000
The demo stack bundles a real data snapshot (Supabase tables, ~1,669 rows) and a canned PARA-DEBATE output, so the dashboard, screener, stock detail, and backtest pages work offline. Add ANTHROPIC_API_KEY to run live agent debates.
A full-stack AI stock intelligence platform that combines a quantitative signal engine with a multi-agent AI analyst debate (PARA-DEBATE), natural-language and voice analysts, and an autonomous trading agent — backed entirely by live, real data.
Why It's Different
Feature
NeuralQuant
Danelfin
TipRanks
Seeking Alpha
Adversarial agent
Mandatory BEAR challenge
No
No
No
India market
~500 NSE names, live
No
No
No
Natural language queries
Yes (Ask Morgan)
No
No
No
Voice analyst
Yes (QuantAstra + Veronica)
No
No
No
LLM hallucination guard
Per-agent metric reconciliation vs live data
No
No
No
Real-time enrichment
RSI/MACD/ATR live
End-of-day
End-of-day
End-of-day
Multi-agent debate
6 agents + head analyst, 1 verdict
Single score
Aggregation
Single author
Pricing
Free / $9.99 / $29.99 / $99.99
Free / $20 / $49 / $99
Free / $30 / $50
$239/yr
Key Features
PARA-DEBATE — 5 specialist agents (Macro, Fundamental, Technical, Sentiment, Geopolitical) + adversarial BEAR challenge + Head Analyst synthesis, run in parallel (asyncio.gather). Each agent's numeric claims are reconciled against live authoritative data before synthesis (hallucination guard). SSE-streamed.
Ask Morgan — natural-language queries with conversation memory and live data injection. "Is AAPL a buy?" → price, P/E, IRS%, QuantFactor breakdown, consensus.
Voice analysts — QuantAstra (on-demand voice) and Veronica (page-aware companion: wake word, morning briefing, reads the page you're on). Deepgram → Claude → LiveKit Inference pipeline on a LiveKit worker.
QuantFactor engine + IRS% — cross-sectional quintile scoring (Growth / Return / Valuation / Risk) vs index peers, distilled into the proprietary Investment Readiness Score (IRS%). US + India.
Hermes — autonomous self-improving trading agent (paper). LLM "reflection" loop mutates one strategy variable at a time with a written rationale and version history. Surfaced at /hermes.
Screener — filter/rank by IRS%, QuantFactor composite, sector, market; presets.
Backtest — walk-forward research tooling. No backtest or performance figures are published.
Dual market — US (S&P 500) + India (NIFTY 500 pool) with India-specific signals (delivery %, India VIX regime).
Payments — Stripe + PayPal subscriptions, 4 tiers. Free during the development phase.
Every number is sourced from live APIs — no synthetic data.
Data Point
Source
Refresh
VIX / India VIX
yfinance ^VIX / ^INDIAVIX
Real-time
S&P 500 vs 200-day MA
yfinance ^GSPC
Real-time
HY Credit Spread OAS
FRED BAMLH0A0HYM2
Daily
Profile / quote / fundamentals
FMP (primary) → yfinance (fallback)
Real-time
QuantFactor quintiles (IN)
Daily "NSE 100/500 Analysis" sheet sync
Daily
P/E TTM / P/B ratio
FMP / yfinance
Real-time
Delivery % (India)
NSE Bhavcopy
Daily
Insider buying/selling
SEC EDGAR Form 4
As filed
RSI-14, MACD, ATR-14, SMA
Finnhub candles
15 min
News sentiment
FMP → Finnhub → yfinance cascade
30 min
Extended / terminal data
OpenBB proxy (nq-openbb)
On demand
The 5-Factor Model (nq-signals)
Scores are computed cross-sectionally within a reference universe — no hardcoded thresholds.
US Market:
Factor
Signal
Weight (Risk-On)
Quality
Gross margin + Piotroski F-score + Accruals
25%
Momentum
12-1 month price return (Jegadeesh-Titman)
25%
Value
Inverse of (P/E rank x 0.5 + P/B rank x 0.5)
10%
Low Volatility
Inverse of realized 1Y vol + beta rank
15%
Short Interest
Inverse of short float rank
10%
Insider
EDGAR Form 4 cluster score
5%
India Market swaps Short Interest for Delivery % (institutional conviction via delivery_pct rank). Regime weights shift automatically — US uses a 4-state HMM; India uses India VIX heuristics (VIX > 25 = Bear, > 18 = Late-Cycle, else Risk-On).
Alongside this, the QuantFactor engine scores each name into quintiles (Growth / Return / Valuation / Risk) vs index peers and derives the IRS% (Investment Readiness Score) shown across the product.
Security
Hardened across a P0–P6 program (Sessions 92–93):
Auth — Supabase JWT verified via JWKS; admin surfaces gated on an ADMIN_EMAILS allowlist (not tier); internal Team Hub behind admin/service-token.
Database — Row-Level Security (migrations 026_enable_rls.sql, 027_security_events.sql); backend uses service_role with RLS as the net.
git clone https://github.com/satyamdas03/NeuralQuant.git
cd NeuralQuant
uv sync
2. Configure (apps/api/.env)
ANTHROPIC_API_KEY=sk-ant-...
FRED_API_KEY=...
FINNHUB_API_KEY=...
FMP_API_KEY=...
SUPABASE_URL=... SUPABASE_SERVICE_ROLE_KEY=... SUPABASE_ANON_KEY=...
[email protected]
# Payments (optional): STRIPE_SECRET_KEY, STRIPE_WEBHOOK_SECRET, PAYPAL_*
# Voice (optional, on the livekit-agent worker): LIVEKIT_*, DEEPGRAM_API_KEY (TTS via LiveKit Inference)
# USE_BEDROCK=true to route Claude calls through AWS Bedrock
3. Run
# API
cd apps/api && ../../.venv/bin/uvicorn nq_api.main:app --reload --port 8000
# Web
cd apps/web && npm install && npm run dev # http://localhost:3000
Security hardening P0–P6 (RLS, headers, rate-limiting, audit log, CI scanning)
In progress / next
Flip CSP from report-only to enforce (after collecting violation reports)
Cut PARA-DEBATE / Ask Morgan cold-start latency (keep-warm)
Multi-year backtest with published P&L / Sharpe / IC
Fitted HMM for India regime (currently heuristic)
Test coverage expansion
Populate growth_percentile in score_cache (currently 0.5 default)
Add /market/indices endpoint for live benchmark quotes
Known Limitations
Cold-start / inherent LLM latency — first-hit Ask Morgan ~50s, PARA-DEBATE ~85s (multi-agent live debate; faster once warm). Run scripts/warmup.py before live demos.
Render auto-deploy — now enabled; verify /health after push for version/cache_age.
CSP report-only — security headers shipped; CSP not yet enforced (no violation collector yet).
India fundamentals gaps — some FMP endpoints are US-only; IN relies on the sheet sync + yfinance.
QuantFactor "earnings declined" flag — derived from profit-growth, not profit level; corrected in UI, full DB correction needs a re-sync.
No persistent Ask Morgan memory — sliding-window context, lost on refresh.
License
Proprietary. See PROPRIETARY-LICENSE.txt. This codebase is offered for acquisition; not open source.
Quant Engine + IRS% · PARA-DEBATE Multi-Agent Debate · Voice Analysts · Autonomous Trading Agent · India & US · 100% Live Data
