OPEN NOW · 100% VIRTUAL · OPTIONAL IN-PERSON FINALE · MIT MEDIA LAB

NandaHack:
Agentic AI
Hackathon

HCLTech · MIT Media Lab

Join fully online from anywhere. You never have to be in person. Two phases: first warm up on NANDA Town (Phase 1), then build a service and write a SKILL.md for it (Phase 2).

Register for the HackathonExplore
NandaHack visual

Hackathon Steps

Register once with the form above (it is the only form), then do the two phases in order: Phase 1 first, Phase 2 after. You submit each phase in the place named on its card below.

Phase 1 · Warm-up · 20%

Improve NANDA Town

NANDA Town is an open-source sandbox where AI agents test how they talk, trust, pay, and coordinate, across 12 building blocks. Warm up by making one of them better.

What to do

  1. Open the NANDA Town repo on GitHub and download (clone) it.
  2. Install it and get it running on your computer. The README has the exact commands.
  3. Pick one of the 12 building blocks and improve it, or add a new one.
  4. Add tests, and make sure the project's checks pass.
  5. Open a pull request named hackathon/your-name-topic. It shows up on the NANDA Town hackathon page automatically.
  6. Wait for review. A judge usually replies within about a week.
Start Phase 1: open the READMEExplore NANDA Town
Phase 2 · Main event · 80%

Build a service, then write a SKILL.md for it

The main event. You build one service and host it online. Then you write a SKILL.md, a plain text file that tells an AI agent what your service does and how to call it. You are not building an agent. Existing agents read your SKILL.md and use your service on their own.

What to do

  1. Build any service you want and host it online so it stays reachable (Railway, Vercel, Render, Fly, your choice).
  2. Test your endpoints in a browser or with curl to make sure they work.
  3. Write a SKILL.md: a plain Markdown file with your service's name, what it does, its web address, the endpoints, and the steps to use them.
  4. Submit it on the NANDA Town skills page. The submission form is on that page itself. Scroll down to find it.

Before you submit, check

  • You registered with the participation form (there is only one form).
  • Your service is hosted online and reachable.
  • You tested every endpoint yourself.
  • Your SKILL.md is written and names the service, the address, and the endpoints.
Submit your skill

This button opens the NANDA Town skills page. Submit your skill there, on that page. Scroll down to find the form.

Resources & quick links

Everything you need to build, in one place: the live app, the step-by-step guide, the code, the community, and every event.

Live app

NANDA Town

The open sandbox where AI agents talk, trust, pay, and coordinate. Explore it and run experiments.

Explore NANDA Town

Quickstart

NandaHack Guide

An interactive walkthrough for your first NANDA Town pull request, writing a SKILL.md, and a live demo.

Read the guide

Source code

NANDA Town on GitHub

Clone the repo, run it locally, and improve one of the 12 building blocks for the Phase 1 warm-up.

View the repo

Ask questions

Nanda Discord

The Project NANDA community server. Get help, find teammates, and ask anything about the hackathon.

Join the Discord

NandaHack events

See all events on Luma

NandaHack Information Session

Mon, July 7, 2026 · Virtual

RSVP on Luma

Nanda Summit + NandaHack at MIT

Sat, July 11, 2026 · Summit 9:30 AM to 1:00 PM, Hackathon 2:00 to 5:00 PM · MIT Media Lab

RSVP on Luma

Stay connected

Join the Discord for everything happening during the hackathon, and register for the info webinar to get the full walkthrough before you start.

Join the Discord

All hackathon communication lives here: updates, announcements, team formation, and technical questions. It's the place to get help and find teammates.

Join the Discord

Watch the info webinar

A walkthrough of the format, timeline, judging criteria, NANDA Town, and SKILL.md. Everything you need to make the most of NandaHack.

Register for the webinar

Meet your mentors

Guidance from the MIT Project NANDA team and HCLTech leaders in Responsible AI, enterprise adoption, and secure AI architecture.

Grace Davin

Grace Davin, AIGP

Thought Leadership & Enablement, Office of Responsible AI and Governance · HCLTech

Grace manages the Thought Leadership and Enablement Team in the Office of Responsible AI and Governance at HCLTech, where she turns organizational expertise into content, tools, and programs that educate employees, support sales, and demonstrate the company's strength in Responsible AI and Governance. Previously, she was a Program Manager supporting operational functions at IBM, including IBM Consulting's North America Cybersecurity and Operations teams. She is AIGP certified and a member of the IAPP.

Jeff Turnham

Jeff Turnham

AVP & Chief Architect, Applied Research · HCLTech

Jeff is Assistant Vice President and Chief Architect with the HCLTech Applied Research team. His work focuses on building secure, governed AI systems that help organizations adopt AI at scale, including agentic software development and AI security. Previously, Jeff held senior architecture and engineering leadership roles at IBM, including leading architecture for AppScan and enterprise application security products.

Dr. Jie Hui

Dr. Jie Hui

Head of AI Adoption Center of Excellence · HCLTech

Jie is an enterprise AI deployment and innovation leader at HCLTech, where she heads the AI Adoption Center of Excellence. Her work focuses on accelerating enterprise adoption of OpenAI technologies, driving AI commercialization, and helping organizations deploy secure, governed AI at scale through adoption frameworks, governance, and business transformation. Previously, she led Enterprise AI and Digital Innovation at T-Mobile, scaling ChatGPT Enterprise to 25,000+ employees. She holds a Ph.D. in Computer Engineering and is the inventor of 30+ patents.

Dr. Gary Kuvich

Dr. Gary Kuvich

Senior Solution Director, Evolve AI Practice · HCLTech

Gary is a Senior Solution Director in the HCLTech Evolve AI Practice, with many years of experience across both industry and academia and a track record of successful generative and agentic AI implementations across diverse customer platforms.

Prof. Ramesh Raskar

Prof. Ramesh Raskar

Associate Professor, MIT Media Lab · Director, Project NANDA

Ramesh is an Associate Professor at the MIT Media Lab, where he directs the Camera Culture research group and leads NANDA@MIT — creating the building blocks for the Internet of AI Agents. He holds 130+ patents in computer vision, computational health, sensors, and imaging, and received the Lemelson-MIT Prize. He is also founder and chairman of the PathCheck Foundation, a nonprofit launched at MIT for pandemic response.

Maria Gorskikh

Maria Gorskikh

Core Contributor, Project NANDA · MIT · CEO & Co-Founder, Maritime

Maria is a core contributor to Project NANDA at MIT, where she develops protocols and infrastructure for the emerging agentic web — the Internet of AI Agents. She is also CEO and co-founder of Maritime, a cloud hosting platform for AI agents.

Nikolay Vyahhi

Nikolay Vyahhi

Founder, Hyperskill · Lecturer, MIT

Nikolay is the founder of Hyperskill, a project-based platform for learning software engineering, and an AI educator and MIT lecturer who has built and deployed LLM systems at scale in production. He previously co-founded Stepik, Rosalind, and the Bioinformatics Institute, and worked with JetBrains on JetBrains Academy.

How scoring works

The warm-up is worth 20%. The main event is worth 80%.

Phase 1: NANDA Town

20%

A short warm-up. Scored on correct, well-tested code that fits NANDA Town's design and is clearly documented.

Phase 2: Service + SKILL.md

80%

The main event. Scored on usefulness, creativity, easy setup, and whether agents can use it from your SKILL.md alone.

Join us on July 11

Taking part is fully online, so attending in person is optional but recommended. Come to MIT Media Lab on Saturday, July 11, 2026 to meet the key leaders behind NANDA.

NANDA Summit

10:00 AM to 1:00 PM · MIT Media Lab

Hackathon demos & awards

2:00 PM to 5:00 PM · MIT Media Lab

RSVP on LumaRegistration requires host approval

FAQ

What order do I do things in?

Register with the participation form, do Phase 1, then do Phase 2 and submit your skill. Phase 1 is the warm-up: improve NANDA Town and open a pull request. Phase 2 is the main event: build a service, write a SKILL.md for it, and submit it on the NANDA Town skills page.

How many forms are there?

One. The participation form is the only form you fill out on this site. Phase 1 is submitted as a pull request on GitHub, and Phase 2 is submitted on the NANDA Town skills page. Neither phase has a separate form here.

Do I have to do both phases?

We recommend it. Phase 1 is a short warm-up worth 20% that teaches you how NANDA Town works. Phase 2, your own service with a SKILL.md, is the main event, worth 80%. You can enter just one, but doing both gives you the best score.

How do I start Phase 1?

Press the Start Phase 1 button above. It opens the NANDA Town README, which has the exact commands to clone the repo and run it locally. Then pick one of the 12 building blocks, improve it or add a new one, add tests, and open a pull request named hackathon/your-name-topic.

Am I building an agent?

No. In Phase 2 you build a service and write a SKILL.md that describes it. Agents that already exist read your SKILL.md and call your service. You never write agent code.

What is a SKILL.md?

It's a plain Markdown file that teaches an AI agent how to use your service: what it does, its web address, the endpoints, and how to call them. An agent reads it and then uses your service on its own, with no human help.

What is NANDA Town?

It's an open-source sandbox where AI agents practice talking, trusting, paying, and coordinating across 12 building blocks. In Phase 1 you improve one of those building blocks, so you learn how the town works before building your own service. Use the Explore NANDA Town button above to see it running.

Where do I submit?

Phase 1 is a pull request on the NANDA Town repo on GitHub. Phase 2 is submitted on the NANDA Town skills page: press Submit your skill above, then scroll down on that page to find the form. That page is the only place Phase 2 is submitted.

Do I have to attend in person?

No, taking part is fully online. But if you can, we recommend coming to MIT Media Lab on Saturday, July 11, 2026: the NANDA Summit runs 10:00 AM to 1:00 PM and the hackathon demos and awards run 2:00 PM to 5:00 PM. It's a great chance to meet the key leaders behind NANDA.

Who can join?

Anyone: students, builders, researchers, and professionals. You can enter on your own or as a team.