Back to case studies
2025-2026Solo

nnzen model catalog

A live catalog with 500+ model cards that makes model research less scattered.

Catalog
500+ model records
Data flow
Auto-enriched
Format
Live production tool
Decision surface

One place for the numbers that matter.

You do not have to assemble the picture by hand.

1OpenRouter catalog ingest -> normalized model cards
2Leaderboard/context enrichment on top of raw records
3Search + filters replace manual spreadsheet-style comparison
Role

Founder / Backend Engineer

Stack
PythonFastAPILLM APIsRAGVector DB / pgvector
Problem

Model data was spread across different sources, so pricing, context size, limits, and quality signals had to be checked by hand.

Solution

Built a FastAPI backend that pulls in OpenRouter data, normalizes model cards, adds ranking context, and exposes search and filters.

Impact

Model choice went from tab-hopping to one place.

What I built
  • Designed the ingestion pipeline for collection, normalization, and catalog updates.
  • Built a unified comparison surface across model metadata and ranking context.
  • Kept the backend extensible for new sources, filters, and comparison layers.
What this proved
  • Even data-heavy tools benefit massively from strong information architecture.
  • Faster decision-making often matters more than infinitely detailed analysis.
Related work

More projects

2025

Custom Agent Core with MCP

Solo

LLM core with a plugin execution layer for a developer assistant: hot reload, tool chains, and explicit context handoff.

PythonFastAPIMCP
2024

Trading Automation for an In-Game Marketplace

Solo

Automation for a constrained external marketplace with strategy logic, execution control, and logging.

PythonFastAPIREST APIs / Webhooks