# Nexus Browser

- **Event:** [Meta Global AI Developer Hackathon](https://cerebralvalley.ai/e/meta-ai-developer-hackathon)
- **When:** Oct 26, 12:00 PM – Nov 4, 9:00 PM (EST)
- **Where:** Online
- **Team:** [Roshan Rateria](https://cerebralvalley.ai/u/roshanrateria)
- **GitHub:** https://github.com/roshanrateria/nexus
- **Demo video:** https://youtu.be/tXm6MvTuUqs
- **Gallery:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/3186

Nexus is an autonomous, stateful multi-agent research browser: you give it one directive (a sentence or a full brief), and a hierarchy of agents plans the work, drives a real Chromium session page by page, verifies every claim verbatim against the raw page text, and compiles a cited report — while a live dashboard shows exactly what the agents are looking at, thinking, and paying.

The problem: real research is tab-juggling. Search engines and chat assistants need constant human prompting, can't traverse multi-step sites (dashboards, publications, paginated docs), and hallucinate numbers with no receipts.

What Nexus does differently:
• Plan–execute–verify loop: a text-only planner splits the goal into steps; a vision executor drives the browser (navigate/click/read/screenshot); a verifier scores every step and routes done / retry / replan — retries stay local, escalations rewrite the plan (video shows a real verifier-flagged re-plan).
• No model grades itself: every claimed quote is re-checked in code against the page's raw text (Unicode-folded matching). Unprovable claims are dropped — a hallucination becomes a retry.
• Zero-trust browsing: robots.txt checked before navigation, page content treated as untrusted data, no stealth scripts.
• Privacy Ledger UI: every LLM call is metered per endpoint and role — calls, tokens, bytes, images, and billed $ — shown live on the dashboard. Planner/reporter are screenshot-blocked by construction.
• One-secret setup, two modes: cloud-only (all Meta) or hybrid (open-weights eyes on Baseten).

Built during the hackathon (full build log in the README's commit-range section): LangGraph topology, the verdict router, the deterministic evidence engine, the Privacy Ledger, the mission-control dashboard (Live/Report/Graph), and the demo-recording kit that produced the submitted 3-minute video from one genuine run — real receipts on screen: $0.22 billed, 24 agent calls, 199k tokens, 10+ sites visited, 4 verbatim-verified evidence quotes, 1 verifier→planner escalation.

## More from Meta Global AI Developer Hackathon

- [Sensei](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/3183)
- [Pheionix](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/3184)
- [KuQTerritory](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/3185)
- [Evidomo](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/3187)
- [Rentropy](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/3188)
- [Gymnos](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/3189)

---

Markdown version of https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/3186. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt