# Ref

- **Event:** [OpenAI GPT-5 Startup Hackathon](https://cerebralvalley.ai/e/gpt5)
- **When:** Aug 9 at 10:00 AM – Aug 10 at 5:00 PM (PDT)
- **Where:** Location TBA
- **Team:** [Matt Dailey](https://cerebralvalley.ai/u/mattdailey)
- **GitHub:** https://github.com/ref-tools/ref-tools-mcp/tree/hackathon-aug-9
- **Demo video:** https://www.youtube.com/watch?v=9AJSInXATP8
- **Gallery:** https://cerebralvalley.ai/e/gpt5/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/gpt5/hackathon/gallery/5

Ref is an MCP server for providing context to coding agents. For this project I explored adding code base indexing.

GPT5 wrote a vectordb, graphdb and text-search index for code that run in a local MCP server. It then wrote a benchmark to evaluate performance and optimized for it. Then, of course, rewrote to Rust.

I also explored GPT5's UI generation using Goose + mcp-ui to have GPT5 generate UI on the fly to visualize the codebase.

---

Markdown version of https://cerebralvalley.ai/e/gpt5/hackathon/gallery/5. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt