Vultr: Agent Rush Hackathon

Build a web-based agent that performs real work - writing and running code or operating a real browser - with every action contained in a sandbox on Vultr. The system should plan tasks, dispatch them to isolated environments, and return verifiable output. Containment-first is required: an agent that only chats is a demo, one that executes safely is a product.

Online build runs 3-8 November 2026, with an on-site phase on 8 November in Salt Lake City, UT. Approved on-site participants showcase their projects live. Travel and accommodation are not covered.

Main challenge: Blast Radius Zero

Pattern A: Sandboxed code execution

• CSV Analyst: upload a spreadsheet, ask questions in plain English, get an executed chart plus the code.
• Prove-It Code Reviewer: run a snippet or PR and its tests in the sandbox, then report what happened.
• Chart Anything: natural language in, executed matplotlib or plotly image out.
• File Fixer: messy CSV or JSON in, cleaned file out, with an executed before/after diff.
• Self-Healing Runner: run code, read errors, patch and retry, with the retry loop visible on screen.

Pattern B: Sandboxed browser use

• Comparison Shopper: two or three product URLs in, screenshot-backed comparison table out.
• Form Filler: structured data in, a multi-step web form filled, with a screenshot trail and an approve-before-submit gate.
• Site QA Sweep: find broken flows and links in a web app, with screenshots and repro steps.
• Research with Receipts: a brief where every claim links to a screenshot of its source.
• Page Watcher: monitor listing or pricing pages, extract structured data, and diff against the previous day.

Containment focus areas

• Process isolation: execution never touches the host or app runtime.
• Secret hygiene: no API keys or credentials inside the sandbox.
• Resource limits: time and memory caps on every run.
• Lifecycle discipline: reset or destroy the environment after each task.

Required stack

• Vultr VM: the backend, acting as the central control and orchestration system.
• Vultr Serverless Inference: all agent LLM calls. OpenAI-compatible, base URL https://api.vultrinference.com/v1, vision-capable models available. Provisioning docs.
• Sandbox boundary: containers or throwaway instances on Vultr, never inside the app process. Docker strongly recommended; OpenSandbox, gVisor and E2B are good starting points.
• Vultr API (optional): spin up and destroy a throwaway instance per task.

Deliverables

• Public GitHub repository with setup and documentation
• Backend deployed on a Vultr VM, with LLM calls through Vultr Serverless Inference
• Public demo URL with a real product-style experience, not just a local demo
• Recorded demo video including one containment moment, such as the sandbox absorbing an rm -rf, an infinite loop, or a hostile web page
• Clear explanation of the architecture and use case

Prizes

$9,000 cash plus $5,000 in Vultr credits.

• 1st place: $5,000 cash + $3,000 Vultr credits
• 2nd place: $3,000 cash + $1,000 Vultr credits
• 3rd place: $1,000 cash + $1,000 Vultr credits

Every participant also gets $200 in free Vultr credits. Prize distribution may take up to 90 days.

Judging criteria

• Application of Technology: how effectively the chosen model(s) are integrated into the solution.
• Presentation: the clarity and effectiveness of the project presentation.
• Business Value: the impact and practical value, considering how well it fits into business areas.
• Originality: the uniqueness and creativity of the solution.

Who can join

Everyone is welcome, regardless of previous AI or coding experience. Teams of 1-6; find teammates on the lablab.ai dashboard or Discord.

Register on lablab.ai and join the lablab.ai Discord - both are required.