phantom-bridge

**phantom-bridge** turns the open web's scattered, real-time news about a public company into a clean, sentiment-scored signal feed. Type a company name; it pulls fresh coverage across seven dimensions — financials, legal/regulatory, leadership, operations & supply chain, deals, products, and reputation — ties every story back to that company, scores each one's financial sentiment with a **local** model, and surfaces it in a live dashboard with scheduled email digests for your watchlist. `Python` · `Streamlit` · `Bright Data Discover` · `distilRoBERTa` · `SQLite` · `Docker` ## What it does - 🔎 **One input, holistic coverage** — a company-anchored prompt library fans out across 7 news categories so you see the whole picture, not just one beat. - 🎯 **On-entity, not noise** — queries lead with the company and results are keyword-filtered to it, so unrelated events don't leak in. - 🧠 **Finance-tuned sentiment, fully local** — every story scored by a distilRoBERTa model running offline (no LLM, no API cost, no data leaving the box). - 📊 **Live dashboard** — analyze any company on demand, manage a watchlist, and configure everything in-app. - 📬 **Scheduled email digests** — a background daemon scrapes, scores, and emails a per-company report on your chosen interval. - 🐳 **One-command demo** — `docker compose up` brings up the dashboard and the watcher together.