#FastAPI

# Safe Scribe by TrustEdge AI **A clinical handoff scribe where the agents argue before they commit, and nothing identifiable leaves the room.** Built in one day at The AI Conference Hack Day 2026 by Erik Jones and Jaiven Spence (TrustEdge AI / Jacobian Engineering) with their agent teams. Repo: https://github.com/erikdj/ai-hackday-2026 ## The problem Clinics want AI scribes. Compliance officers say no, twice: patient data would leave for a hyperscaler LLM API, and afterwards nobody can prove…

Agent Foundry — Debug your AI agents like software. Agent Foundry is a local-first reliability and provenance debugger for AI agents. It shows why an agent behaved differently, where a run first diverged, what evidence and tools influenced its decision, and whether the behavior can be replayed. Our Hack Day demo uses a simulated autonomous biology workflow based on the Moddik plate architecture. Deterministic sensor events become independently addressable evidence, are committed into verified…

# AccountPulse - **What it is:** an AI early-warning system that tells customer-success teams which customers are about to leave, why, and what to send them. - **How:** CRM data + live news + competitor traffic → scored by Crusoe → fact-checked by Nebius → stored as a Neo4j graph → shown in the dashboard.  ## Live demo in 3 terminals - **1. Backend:** `cd backend && source .venv/bin/activate && uvicorn app:app --reload --port…

Full-Stack Self-Healing DevOps & Security Copilot The Concept: An AI operations engineer that doesn't just suggest code fixes—it monitors cloud infra, detects uptime/security drops, automatically provisions fixes, and generates audit reports for enterprise compliance.

AI agents on Vultr that prove a bank's new payment system handles money exactly like the old one before launch, with every test human-approved and run in throwaway gVisor sandboxes.

Sandbox inside of a sandbox. Agent codebase remediation.

Tieout is AI month-end close for accounting firms: one click reconciles every client's bank account, with an agent that writes and runs real Python for each client.

X/Mine runs self-driving mining trucks on Vultr and replays every failure exactly, so an AI agent can find a fix in simulation that ships only once it's proven safe and a person approves it.

Sheltr turns one phone photo of a flood-damaged room into a 3D room model, priced damage estimate, evidence PDF, survivor-approved aid claim form, and scam-link verifier, with risky steps isolated in disposable Vultr microVMs.

An autonomous AI fashion publication where specialized agents research trends, debate the evidence, and safely stage, review, and publish stories from isolated sandboxes.

What are people doing with our AI, and what isn't working for them? logless tells you without anyone reading your private chats.

A PR check for ML training code that executes the math instead of reading the diff, in gVisor sandboxes on Vultr, behind NetBird with zero open ports.