# Anurag Dhungana

> I believe in doing hard things, shipping fast, and learning obsessively. This is my corner of the internet where I share what I am building and learning.

🎓 MSCS @ GW George Washington University

🤖 Prev Machine Learning Engineer @ Cheers (YC S24)

🏎️ Formula 1 enthusiast

📍 Washington, DC, United States

🧩 Currently focused on agent infrastructure, memory, and evaluation systems for different verticles

## Contact

- Email: [hey@anuragd.me](mailto:hey@anuragd.me)
- GitHub: [@Aarekaz](https://github.com/Aarekaz)
- LinkedIn: [anuragdhungana](https://www.linkedin.com/in/anuragdhungana)
- Website: https://www.anuragd.me

## Featured Projects

- [Shrimp](https://github.com/Aarekaz/shrimp): Open source agent harness — pluggable memory, sub-agents, browser control, and 1000+ app integrations. The model is the brain, Shrimp is the body.
- [SwitchBoard](https://github.com/Aarekaz/switchboard): Imagine there was a library that would allow you to write an AI agent bot once, and imagine it provided great 2026-level DX, and then, magically, it just worked on Slack, Teams, Google Chat, and Discord without writing platform-specific code.
- [Metro MCP](https://github.com/Aarekaz/metro-mcp): Model Context Protocol server for real-time transit information across DC Metro and NYC Subway systems. Built on Cloudflare Workers with OAuth 2.1 authentication. Used by about 2K+ people daily
- [Personal API](https://github.com/Aarekaz/api): Personal API to manage my website, personal content and all personal digital database
- [Session Base](https://github.com/sessionbase/cli): Capture, organize, and share sessions across coding agent platforms, helping you and your dev team preserve valuable context.
- [SEAS Search](https://github.com/itsmepraks/SEAS_Search): Knowledge graph-based course QA system that fine-tunes Llama 3.1 with Graph-RAG to answer questions about GWU SEAS courses, schedules, and prerequisites.

See all at https://www.anuragd.me/projects.md

## Recent Writing

- [Harness engineering](https://www.anuragd.me/blog/agent-harnesses-explained.md): Harness engineering is the work of turning models into systems you can operate, inspect, and trust: tools, memory, permissions, feedback loops, and stopping conditions.
- [the brain is easy. the body is hard.](https://www.anuragd.me/blog/the-brain-is-easy-the-body-is-hard.md): draft, notes on building agents
- [tinkering](https://www.anuragd.me/blog/tikering.md): Today is a great day to build
- [Mantras](https://www.anuragd.me/blog/mantras.md): Personal mantras and principles I live by—things I try to read every day to stay focused and grounded.
- [Go after the hardest thing](https://www.anuragd.me/blog/go-after-the-hardest-thing.md): Why we should chase the toughest challenges—not because they're easy, but because they're hard. Our duty to future generations.
- [thoughts on background coding agents via Tembo](https://www.anuragd.me/blog/tembo.md): Exploring the potential and implications of background coding agents through the lens of Tembo's approach to autonomous development.
- [Working at Cheers (YC S24)](https://www.anuragd.me/blog/working-at-cheers.md): Reflecting on my transformative summer internship at Cheers, a YC S24 company building the future of customer engagement.
- [Hello, world — this site](https://www.anuragd.me/blog/hello-world.md): A quick note about how this website is put together and why it exists.

See all at https://www.anuragd.me/blog.md

## Other Pages

- [Resume](https://www.anuragd.me/resume.md): work experience, education, skills
- [Photography](https://www.anuragd.me/photography.md): photo gallery
- [Now](https://www.anuragd.me/now.md): current focus
- [Uses](https://www.anuragd.me/uses.md): tools and gear
- [Shelf](https://www.anuragd.me/shelf.md): curated quotes, links, visuals

---

Source: https://www.anuragd.me/

Index of all content: https://www.anuragd.me/llms.txt