EdgeGuard: Multi-Modal Consensus Broker

Created by team Code Voyagers on September 16, 2026

AI/ML API Anthropic Claude Claude Code Groq Vercel

Intel Online

Robots and self-driving machines need absolute certainty about their surroundings before they make a move. Our project acts as a real-time safety checkpoint for these autonomous systems. Instead of relying on a single point of failure, it constantly compares live data from multiple different sensors, including cameras, depth monitors, and lasers. Think of it as a team of spotters double-checking each other's work. If one sensor gets blinded by a glare, gets covered in dirt, or suddenly starts giving bad readings, our system catches the error immediately. It overrides the confused sensor, raises a high-risk warning, and completely stops the machine from making a dangerous physical movement. To show this in action, we built a live web dashboard. During our demonstration, viewers can use a slider to manually break a sensor reading on purpose. You can watch our system instantly spot the outlier, sound the alarm, and hit the brakes in real-time, proving that the machine only moves when it is objectively safe.

Category tags:

Coding, Web Application, Productivity, Agent Builder track - The INTERNET OF AGENTS

Github Presentation Demo

Explore more applications

Quarantine

An AI agent that writes and runs real code in throwaway gVisor sandboxes on Vultr: no network, no secrets, hard caps, destroyed after each run. Every run ends with a signed containment receipt proving what the code could and couldn't touch.

Quarantine

SLATE: Receipts for Every Agent Action

SLATE is a browser agent that works inside a throwaway microVM on Vultr. Every step is checked by a second model, hash-chained and signed with Ed25519, and a person approves the final action. If it is not on the slate, it did not happen.

NoBanks

VULTRQwen3NVIDIAClaude Code

testtinggg

good tingood tingood tingood tingood tingood tingood tingood tingood tingood tingood tin

LFG

Detonation Chamber

Run an untrusted npm/PyPI package, GitHub repo, or URL in a sealed, disposable Vultr sandbox. Watch what it does and get a verdict based on its actual behaviour. Every escape attempt is contained and recorded.

Builders Nepal

Containment Foreman - sandboxed agent runtime

A human-gated foreman that plans AI agent tasks, dispatches each step to a disposable, network-less Docker sandbox, and returns verifiable receipts with SHA-256 artifacts, resource caps and zero host access.

Schultzenator

Upcoming AI Hackathons
For Innovators & Creators

Explore more applications

Quarantine

An AI agent that writes and runs real code in throwaway gVisor sandboxes on Vultr: no network, no secrets, hard caps, destroyed after each run. Every run ends with a signed containment receipt proving what the code could and couldn't touch.

Quarantine

SLATE: Receipts for Every Agent Action

SLATE is a browser agent that works inside a throwaway microVM on Vultr. Every step is checked by a second model, hash-chained and signed with Ed25519, and a person approves the final action. If it is not on the slate, it did not happen.

NoBanks

VULTRQwen3NVIDIAClaude Code

testtinggg

good tingood tingood tingood tingood tingood tingood tingood tingood tingood tingood tin

LFG

Detonation Chamber

Run an untrusted npm/PyPI package, GitHub repo, or URL in a sealed, disposable Vultr sandbox. Watch what it does and get a verdict based on its actual behaviour. Every escape attempt is contained and recorded.

Builders Nepal

Containment Foreman - sandboxed agent runtime

A human-gated foreman that plans AI agent tasks, dispatches each step to a disposable, network-less Docker sandbox, and returns verifiable receipts with SHA-256 artifacts, resource caps and zero host access.

Schultzenator