✦ AstraNexus

Your inbox, as a navigable galaxy.

Unsupervised email organizer. A fine-tuned multimodal encoder (MiniLM text + SigLIP vision, LoRA) embeds every email; HDBSCAN groups them into constellations that NVIDIA Nemotron-3-Nano-4B names and reasons over; threads spanning accounts surface as wormholes. No rules, no folders — the structure is discovered.

Launch the demo →

Color — the constellation (topic the encoder grouped it into). Each has a Nemotron-named hub star.

Size — unread (big) vs read. Brightness ∝ urgency.

Gold halo — the email carries an image (where the multimodal model earns its keep).

Pink dashed — a wormhole: one thread across two accounts.

Under the hood: the whole AI pipeline runs on a Modal GPU as a LangGraph agentic graph — fetch→embed→cluster→label→judge→serialize. An LLM-as-judge (Nemotron) scores the labels and loops back to relabel until they pass, then it writes an open agent trace — view the latest trace.json →. An in-app A/B toggle pits the fine-tuned encoder against off-the-shelf SigLIP; layered fallbacks (Modal → NIM-hosted Nemotron → keyword heuristic) keep it alive.

About the data: the default fixture is a synthetic dataset built only for demo/testing — no real email. Google restricts reading people's mail, so live Gmail is invite-only (approved test accounts / my own mailboxes); session-only, never stored.

🧠 Nemotron-3-Nano-4B⚡ Modal GPU 🕸 LangGraph + judge loop🎯 Fine-tuned encoder + A/B 📡 Open agent trace

Fine-tuned encoder: DriptoBhattacharyya/astranexus-mm-encoder · built for the Build Small hackathon.