The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
🕵️ RealityOS: The Hollow Hour — What if reality itself was hiding the evidence?
Built with @Base44 for the #Base44Challenge 🚀
A woman has disappeared from reality. The official records say she was never there. But the evidence tells a different story.
Welcome to RealityOS, a cinematic, interactive sci-fi detective mystery where every clue matters and your decisions determine the ending.
🔎 Investigate the impossible
Examine mysterious records, airport surveillance, and hidden clues.
Connect evidence to uncover contradictions in the timeline.
Decode a terminal and unlock a concealed room.
Discover what happened during the mysterious 11-second gap.
🧩 The mystery doesn't end with finding the truth.
Choose your verdict:
RESTORE — Bring her back.
PRESERVE — Keep her frozen in the archive.
CONTAIN — Seal the truth away.
EXPOSE — Reveal the impossible to the world.
Four choices. Four different outcomes. One mystery for you to solve.
It took around an hour of investigating with ChatGPT's help to work through the clues, uncover the hidden room, validate the evidence connections, and explore all four endings.
This project is an experiment in making an AI-built application feel like a playable world rather than just another dashboard.
🎮 Play RealityOS: The Hollow Hour
Built with @Base44 for the #Base44Challenge.
Would you RESTORE, PRESERVE, CONTAIN, or EXPOSE? 👀
This looks fantastic! 🤩
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
The Base44 Challenge is LIVE!!
Check out the guidelines HERE and show us how creative you can get 🚀
Need inspiration? Check out the top submissions from our last Base44 challenge: 1st Lilly Blick, 2nd Sergey Bertagnini, 3rd Pri Patel
Project AIR is an open-source toolkit that keeps a tamper-proof record of what AI agents do. Every action an agent takes gets signed, chained to the step before it, and tied to the person who authorized it. The chain is anchored to Sigstore Rekor, a public transparency log, so anyone can check later that nothing was changed or deleted. When something goes wrong, you can show exactly what happened and who approved it, instead of just saying it happened.
It also runs 16 detectors over every record, covering all ten risks on the OWASP Top 10 for Agentic Applications, three from the OWASP list for LLM apps, and three of its own. It can stop an agent mid-action until a person signs off. It plugs into LangChain, LlamaIndex, and the OpenAI, Anthropic and Gemini SDKs with a line or two of code.
I built the Python library and command-line tool, published on PyPI as projectair (now at version 1.3.1) under the Apache 2.0 license, plus the website and dashboard in SvelteKit. We run it on our own infrastructure too: every request to vindicara.io is recorded and anchored to Rekor every minute.
Impressive work! 👏 Excellent approach to AI agent security, tamper-proof audit trails, and human oversight for more trustworthy AI systems.
In security operations, every second matters. SentriGo is an AI-powered mobile app designed to help on-site guards detect, assess, and respond to potential threats in real time.
The experience follows a simple Scan, Classify, Alert workflow. Guards can capture a scene, receive AI-powered threat analysis with confidence scores and risk indicators, and connect with dispatch. A visual incident timeline keeps them informed about AI verification, incident status, and dispatcher responses.
A high-contrast dark interface, strategic color accents, large interactive elements, and clear hierarchy support fast decision-making in demanding environments.
Explore the project on Dribbble:
https://dribbble.com/shots/27820478-Mobile-App-Security-Guard-Assistant-App
The simple Scan, Classify, Alert workflow is perfect for guards under pressure. That high-contrast dark interface with the threat-level screen looks built for real field conditions.