Local-first AI chat / SELECTED ENGINEERING WORK
Nuvio
A responsive web interface for local AI conversations with streaming responses and persistent history.
This overview describes my engineering work on this project, including its purpose, implementation, and technical focus. Project illustrations are abstract; private assets and internal implementation details are not published here.
Overview
A responsive web interface for local AI conversations with streaming responses and persistent history. My work connects the user experience with the data, application logic, and integrations behind these workflows.
Problem addressed
Local models need a usable chat interface and controlled demo access without exposing the model service directly.
Solution
Built a Next.js and TypeScript MVP around Ollama, with SQLite and Prisma storage, passcode sessions, and a Cloudflare Tunnel demo.
Key features
- Streaming model responses
- Persistent conversation history
- Installed-model selection
- Passcode sessions
- Prompt and per-IP rate limits
- Health checks and controlled demo access
Technical outcome
A local AI chat MVP with persistent conversations and secure public demo access without exposing the Ollama service.
Interested in the engineering behind this work? Get in touch to discuss the approach and a similar product.