# Projects

> Things I have made, from AI benchmarks and small tools to bronze maps and trading cards.

Canonical page: https://gregkamradt.com/projects

Experiments, useful tools, and things I wanted to exist.

## [RunReq](https://runreq.com/)

2026-08-17

A hiring monitor that turns frontier AI job boards into analysis of current hiring activity and historical changes over time.

![RunReq](https://gregkamradt.com/images/RunReq.png)

## [ReadSide](https://readside.dev/)

2026-06-19

Paste any article URL for a clean, distraction-free reading view, then highlight any passage to start a threaded chat about that exact section.

![ReadSide](https://gregkamradt.com/images/ReadSide.png)

## [InterAuth](https://interauth.dev/)

2026-06-08

A pass-through broker that hands your agent a disposable, read-only share address for Google Docs. No OAuth, no install, no signup - share a Doc, revoke anytime, just like with a colleague.

![InterAuth](https://gregkamradt.com/images/InterAuth.png)

## [agnts.sh](https://agnts.sh/)

2026-05-21

A link service built for agents. Every URL serves three response shapes from the same endpoint - an HTML stub for humans, raw markdown for agents, and full JSON - based on the request's Accept header. Skip the scraping, just hand your agent a link.

![agnts.sh](https://gregkamradt.com/images/agnts.png)

## [TBPN Limited](https://www.tbpnlimited.com/)

2025-10-29

Phsyical trading cards based off of popular TBPN moments

![TBPN Limited](https://gregkamradt.com/images/tbpnlimited.png)

## [Agent Traffic Control](https://www.agenttrafficcontrol.com/)

2025-09-08

A UX exploration combining radar charts and agentic work.

![Agent Traffic Control](https://gregkamradt.com/images/ATC_OG.png)

## [I Vibe More Than You](https://www.ivibemorethanyou.com/)

2025-06-16

Meme site that allows you to open up as many vibe terminals you want.

![I Vibe More Than You](https://gregkamradt.com/images/vibemore.png)

## [SnakeBench](https://x.com/gregkamradt/status/1722386725635580292)

2025-03-11

50 LLMs battle it out on Snake.

![SnakeBench](https://gregkamradt.com/images/SnakeBench.png)

## [Needle In A Haystack](https://x.com/gregkamradt/status/1722386725635580292)

2024-09-16

I created a benchmark to test how well LLMs can recall information from a long context window. It was tested on gpt-4o & claude-2.1

![Needle In A Haystack](https://gregkamradt.com/images/NeedleHaystack.png)

## [Terra Mano](https://terramano.co/)

2024-09-16

In need of a physical project, I managed 3d printing, casting in bronze, and hand finishing maps of US mountains.

![Terra Mano](https://gregkamradt.com/images/TerraMano.jpg)

## [ChunkViz](https://chunkviz.up.railway.app/)

2024-09-16

LLMs do better with shorter context windows. I built a tool to visualize how different chunking strategies to help you pick the one that is best for your use case.

![ChunkViz](https://gregkamradt.com/images/ChunkViz.png)