inferred from GitHub
audioslp kit
Core trick
Real-time voice conversation with an LLM-played patient, graded by a second model against a curated guideline registry.
Evidence
README matched "Opus 4.7 hackathon": Built in three days for the Opus 4.7 hackathon by a medical-doctor-turned-software-engineer ([@bedriyan](https://github.com/bedriyan)), using Claude Code with Opus 4.7.
README excerpt
# medkit Browser-based ER + polyclinic clinical training simulator. You play the doctor: new patients arrive at triage, you talk to them in real time, order tests, treat, disposition. An attending physician (Claude Opus 4.7) watches and grades your decisions. > Hackathon submission. Cases are plausible but synthetic — no clinical claims. --- ## About Medkit is a voice-first AI patient simulator for medical students and newly graduated doctors. You take the history, order labs, read imaging, diagnose, and prescribe — talking to AI patients in real time. After each session, an attending grader powered by Claude Opus 4.7 marks your communication, history-taking, and clinical reasoning, citing published guidelines (NICE, ESC, AHA, GINA, GOLD) from a curated registry so the grading can't fabricate sources. The format is modelled on OSCE training with standardised patients, which works well but is expensive, scheduled rarely, requires physical attendance, and isn't available in many countries — leaving most trainees globally with little or no access. Medkit makes the same kind of practice available on demand in the browser. Built in three days for the Opus 4.7 hackathon by a medical-doctor-turned-software-engineer ([@bedriyan](https://github.com/bedriyan)), using Claude Code with Opus 4.7. --- ## What's inside | Layer | Tech | |---|---| | Frontend | React 18 + TypeScript + Vite, Three.js (`@react-three/fiber`, `@react-three/drei`) | | Voice transport | LiveKit Cloud (WebR