Footer navigation

Unlocking state-of-the-art artificial intelligence and building with the world's talent

LinkedIn
Twitter/X
Instagram
Discord
YouTube
Twitch

Other group brands:

Links

AI Tech
AI Hackathons
AI Tutorials
AI Applications
NativelyAI
AI Articles
Leaderboard
Writers

lablab

Brand
Hackathon Guidelines
Terms of Use
Code of Conduct
Privacy Policy
Security

Get in touch

Discord
Sponsor
Cooperation
Contribute
Send email

© 2026 NativelyAI Inc. All rights reserved.

3.86.0

Help CenterBrowse FAQs and guides.

Discord CommunityChat with mentors and the team.

Challenge + Get $100 creditsAI Hackathons AI Apps AI Tech AI Tutorials AI Articles NativelyAI Sponsor

AI app: AgentRush — Blast Radius Zero for Vultr: Agent Rush Hackathon

Home
App Discovery
AgentRush — Blast Radius Zero

AgentRush — Blast Radius Zero

Created by team AgentRush - Kosoyy on November 04, 2026

VULTR DeepSeek V3 OpenAI rest api

AgentRush is a sandboxed execution agent built for the Vultr Agent Rush hackathon. A user submits a task in the web UI; an LLM on Vultr Serverless Inference decomposes it into steps; URL fetches run on the orchestrator host with SSRF-pinned DNS; generated code executes inside a fresh Docker container per task: no network, read-only root fs, tmpfs workdir, capped memory/CPU/pids, all capabilities dropped, empty environment, wall-time kill, destroyed after the run. Every run returns a verifiable JSON record with per-step commands and sha256 of outputs. The demo video shows six live attacks — rm -rf, infinite loop, fork storm, env scrape, outbound curl, prompt injection — each dying at its intended boundary. Live public deployment on a Vultr VM (fra).

Category tags:

Agent Builder track - The INTERNET OF AGENTS, Vultr Track - Raise, Security, Developer Tools, Productivity

Github Presentation Demo

Explore more applications

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

Ghostfox Zero: Browser Agent

A sandboxed browser agent powered by our own Firefox engine. True agentic loop with vision verification, human approval gate, and MCP endpoint for AI agents.

autokeren

AgentOpsAIMLVULTR

LeakProof

Finds revenue leaks in billing exports without letting the data leak: model-written pandas runs in a throwaway gVisor sandbox on Vultr (no network, no secrets, hard limits), a second model checks every sentence, and each answer has a re-runnable receipt.

Design Master Solutions

kosoyyagent602

Upcoming AI Hackathons
For Innovators & Creators

Explore more applications

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

Ghostfox Zero: Browser Agent

A sandboxed browser agent powered by our own Firefox engine. True agentic loop with vision verification, human approval gate, and MCP endpoint for AI agents.

autokeren

AgentOpsAIMLVULTR

LeakProof

Finds revenue leaks in billing exports without letting the data leak: model-written pandas runs in a throwaway gVisor sandbox on Vultr (no network, no secrets, hard limits), a second model checks every sentence, and each answer has a re-runnable receipt.

Design Master Solutions