
Cascade AI
Four Gemini agents autonomously onboard B2B clients. Upload a contract PDF, paste a brief, and agents research the client, send personalized emails, build project plans, flag risks, and handle intake submissions without human triggers.
See what developers build and ship on Vultr.

Four Gemini agents autonomously onboard B2B clients. Upload a contract PDF, paste a brief, and agents research the client, send personalized emails, build project plans, flag risks, and handle intake submissions without human triggers.

RLForge takes any arbitrary academic paper or spec from a verifiable field - and automatically creates an RL environment.

We made the world's fastest, cheapest, and most accurate browser use on Vultr and it doesn't even use vision.
Points, levels & badges
Enter challenges & submit builds
Register to events & meetups
Get your work featured

FloatGPT is an omnipresent desktop AI companion that floats over Windows to automate OS workflows, plan tasks, and generate real-time executive dossiers. Operating 100% privately on your PC or powered by the cloud, it transforms daily computing with screen awareness and calm execution.

ClaimTrace audits the citations in a scientific manuscript: it checks that every reference exists and is described correctly, and that each cited source actually says what the citing sentence claims, with a verbatim quote as evidence. On 1,728 reference test cases it never marked a fabricated or altered reference as verified.

When a lecturer says “look at this chart”, blind and low-vision students hear nothing. SeeHere watches a recorded lecture, finds what is on screen but never said aloud, and writes short audio descriptions that a CP-SAT solver fits into natural pauses. Every line is linked to its evidence (keyframe, OCR, transcript) and checked, and uncertain claims are held for an instructor. Live on Vultr Cloud Compute with Vultr Serverless Inference.

Code review is a daily job skill that almost nobody is taught. Review Dojo gives students realistic pull requests with planted bugs, security holes and performance flaws. You comment on lines you distrust, get scored against a hidden answer key, earn XP, unlock harder missions, collect achievements and climb a leaderboard. Optional AI sensei feedback explains what you missed. Built with React, TypeScript, FastAPI and PostgreSQL, and deployed with Docker on a Vultr Compute instance.

An AI-powered research agent that gathers information from multiple sources and generates structured, actionable pre-meeting briefings.

6-in-1 multispectral agent for Food, Room, Derma, Naphtol, Forensic and Gem check. IMX219 + MLX90640 Thermal + NDIR 4-channel on Vultr, with Bio Healthy Room monitoring and certificate printing.

Tally opens every supplier invoice in a throwaway Microsandbox microVM on a Vultr VX1, reads only its page images with two model families on Vultr Serverless Inference, and lets fixed rules, not a model, decide what is held. A voice desk device announces each hold.

Four Gemini agents autonomously onboard B2B clients. Upload a contract PDF, paste a brief, and agents research the client, send personalized emails, build project plans, flag risks, and handle intake submissions without human triggers.

Ocean buoys feed disaster-warning centres, which trust what they receive. A hacked buoy can fake giant waves to trigger a false alarm, or hide a real storm. SeaShield AI checks every reading with four layers: cryptographic signatures, physics rules learned from real data, an AI anomaly model, and comparison with nearby buoys. Suspicious alerts are held for human review. Our live demo on Vultr replays real NOAA data from Hurricane Helene: launch attacks yourself and watch SeaShield stop them.

Suraksha is a voice companion on a Galaxy Watch and a tablet for parents who live alone. It talks with her in Hindi or English and acts on what she asks (WhatsApp her son, set a reminder, remember where the spare key is), reminds her about her medicines, and when the watch detects a fall it asks her first, then gets the family member who can actually reach her. Runs end to end on Vultr.

CoercionGuard is a firewall between an AI agent and the web page it’s about to agree to. It reads the page, flags hidden fees, renewals and pre-ticked add-ons that go beyond what the user asked for, and stops the agent before anything is sent to the site.

AI agents are becoming part of everyday business operations, but giving them access to sensitive company data creates serious security and privacy risks. Borrow solves this by giving AI agents access only to the specific information they need, for a limited time, with clear permission. For example, when an employee asks an AI agent to prepare an expense report, Borrow grants access to the required expense data without exposing the rest of the company's records.In short Security with Trust!.