Agent Stack 48 | AI Agents & Tools Hackathon | LabLab
NativelyAI × LabLab
Registration open 48-hour online hackathon Dec 11–13, 2026

Agent Stack 48

AI Agents & Tools Hackathon

Build specialized AI agents or the tools that power them.

Join a 48-hour hackathon focused on building practical AI systems. Create a specialized agent that solves a specific real-world problem, or develop tools, APIs, MCP servers, and integrations that extend what AI agents can do. Two tracks, one competition, and the freedom to build with the technologies you choose.

01 Reason Plan the work.
02 Connect Use tools & systems.
03 Act Move the task forward.
04 Prove Return a real outcome.
START Dec 11 · 17:00 CET
Q&A on Discord one hour after kickoff Join Discord →
Enroll Read the challenge Submissions close Dec 13 · 17:00 CET
About

Build what’s next for AI agents.

Agent Stack 48 is a 48-hour hackathon for developers building specialized AI agents and the tools that power them. From vertical agents solving industry-specific challenges to MCP servers, APIs, and toolkits that unlock new capabilities, the focus is on creating practical, working technology.

The brief
48H

Build something useful

Ship a working specialized AI agent or an agent-ready tool, integration, or toolkit. Your project should address a clearly defined problem or capability gap and demonstrate practical functionality.

Dec 11 · 17:00 CET → Dec 13 · 17:00 CET
Open stack

Bring your own stack

Use the models, frameworks, APIs, MCP servers, cloud services, and developer tools that make sense for your build.

Live support

Q&A at 18:00 CET

One hour after kickoff, join the LabLab Discord for the live Q&A session and event support.

Challenge

Build an agent with a purpose. Or the tools that make agents possible.

The next generation of AI isn’t just about smarter agents. It’s also about the tools that allow them to interact with the world.

Agent Stack 48 challenges developers to build either highly specialized AI agents designed for specific industries and workflows, or the tools and infrastructure that enable agents to access information, interact with systems, and perform meaningful actions.

Whether you’re building a vertical agent or a reusable toolkit, the goal is the same: solve a real problem, build something functional, and demonstrate its value.

Track 01

Specialized AI Agents

Build an AI agent designed to solve a specific problem within a defined industry, profession, or workflow. Focus on depth, reliability, and practical results rather than general-purpose functionality.

Track 02

Tools & Toolkits for AI Agents

Build tools that extend what AI agents can access, understand, or do. These can be standalone APIs, MCP servers, SDKs, connectors, integrations, or reusable toolkits that enable agents to interact with external systems.

Two tracks. One competition. Both tracks compete for the same prizes and are evaluated on technical execution, innovation, practical utility, and demonstrated functionality. You don’t need to build a complete agent to submit a tool or toolkit.
01 / DEFINE

Find a real problem

Identify a specific workflow, industry challenge, or missing capability that your agent or tool will address.

02 / BUILD

Create your solution

Develop a specialized AI agent or build a tool, API, MCP server, or toolkit that enables new agent capabilities.

03 / DEMONSTRATE

Prove it works

Show your solution in action through a working demo, real integration, or reproducible workflow.

Technology

Your stack. Your choice.

Build with the models, frameworks, APIs, development tools, and infrastructure that best fit your project. Whether you’re creating a specialized agent or developing tools for other agents, there are no mandatory technologies or providers.

Resources

Everything you need to start building.

Start with a few useful resources, or bring your own stack. None of these tools are required.

Event Schedule

All times are in Central European Time (CET).

Kickoff & build starts

The 48-hour build window begins immediately after the kickoff briefing. Start building from this point and continue until the submission deadline.

Start
Live Q&A on Discord

Bring setup, challenge, technology, and team questions one hour after kickoff. Join the LabLab Discord →

Live session
Build continues

The build window remains open continuously. Develop, connect tools, test the workflow, and keep shipping.

Build
Submission closes

The 48-hour build window ends. Complete and submit your project page, repository, demo, and submission materials by 17:00 CET.

Deadline
Referral board

Bring builders into the relay.

Once your enrollment is approved, generate your personal referral link from the event dashboard, share it with builders, and watch your community score grow.

Community leaderboard

Referral points are a visible community score. They do not affect project judging or winner selection, and there is no separate referral prize pool.

200points per successful referral
1

Get approved

Enroll in Agent Stack 48 and wait until your participation is approved.

2

Generate your link

Open your event dashboard and generate your personal referral link.

3

Share & track

Invite builders and follow referral activity from the dashboard and live leaderboard.

+200You earn points when someone joins through your link and submits a project.
+100The referred participant earns points when they submit their project.
Referral activity is tracked separately from project judging and winner selection. Keep sharing your link and follow your position on the community leaderboard.
Prizes

Prize structure coming next.

Agent Stack 48

Prize pool · TBA

One competition, two tracks, one set of winners. Whether you build a specialized AI agent or a tool that extends agent capabilities, your project competes for the same prizes. Full prize details will be announced before the hackathon begins. All project building must take place during the official 48-hour build window.

Details to be announced
Submission

Make the work easy to verify.

A strong submission clearly demonstrates what you’ve built, the problem it solves, and how it works. Whether you’re submitting a specialized agent or a standalone tool, judges should be able to understand its purpose, technical implementation, and practical value.

Project

  • Project title and clear description
  • Working specialized AI agent, tool, API, MCP server, integration, or toolkit
  • Track selection: Specialized AI Agents or Tools & Toolkits for AI Agents
  • Technology and category tags
  • Technical architecture and explanation of how the agent or tool works, including its intended use case and relevant integrations

Proof

  • Public GitHub repository
  • Demo or application URL
  • Recorded demo video
  • Cover image and presentation materials
For tool and toolkit submissions, demonstrate how your solution can be used by an AI agent or integrated into an agentic workflow. Building a complete agent application is not required.
FAQ

Before you build.

What qualifies as a specialized AI agent?

An agent designed to solve a clearly defined problem within a specific industry, profession, or workflow. We encourage focused, purpose-built agents rather than general-purpose assistants or basic chatbots.

Can I submit a tool without building an agent?

Yes. Tools and toolkits are an equally important part of Agent Stack 48. You can submit MCP servers, APIs, SDKs, integrations, connectors, or other solutions that extend the capabilities of AI agents. A complete agent application is not required.

Are there separate prizes for each track?

No. Both tracks compete for the same overall prize pool. Projects are evaluated based on their technical quality, innovation, practical utility, and demonstrated functionality.

Do I have to use specific technologies?

No. Agent Stack 48 is an open-stack hackathon. You’re free to use whichever models, frameworks, APIs, infrastructure, or development tools best suit your project. Native.Builder is available as an optional development resource, and new Native.Builder users receive 50 free credits.

Do I have to use MCP?

No. MCP is one way to build tools for AI agents, but custom APIs, SDKs, direct integrations, and other architectures are equally welcome.

When is the live Q&A?

December 11 at 18:00 CET — exactly one hour after kickoff — in the LabLab Discord.

Do referral points affect judging?

No. Referral points are a separate community leaderboard and do not affect project judging, prizes, or winner selection.

When are prize details announced?

The prize structure will be added to this page before the hackathon begins.