LiftCast: A Local-First AI Workout Forecaster Built for a Friend

Описание и применение

LiftCast — локальный AI‑логгер тренировок, который преобразует неструктурированные сообщения в структурированные данные, прогнозирует прогресс, определяет плато и воспроизводит аудио‑обзор, работая полностью офлайн.

Задача

Armaan never logs workouts, so he cannot assess strength progress or stalls.

Результат

LiftCast provides structured logging, progress forecasting, plateau detection, and audio briefing entirely offline, enabling Armaan to track strength progress without manual entry.

Рабочий процесс

• Paste WhatsApp note into 10‑second shorthand logger
• Gemma parses note into JSON schema
• Data stored locally
• TabPFN forecasts next session top set with 95% CI
• 56‑day regression flags stalls
• Barbell visualizer shows plate layout
• ElevenLabs synthesizes 10‑second audio recap
• Play recap in gym earbuds

Доказательства

LiftCast is a local‑first tracker and strength forecaster built for his workflow

Источник

10‑Second Shorthand Logger: Pastes raw text, typos, or Hinglish notes. A local Gemma model parses them into structured sets via an enforced JSON schema.

Источник

In‑Context Progress Forecaster: Prior Labs' TabPFN runs locally on CPU to forecast his next session's top set with calibrated 95% prediction intervals.

Источник

Plateau Detection & Barbell Visualizer: Uses a 56‑day regression slope to flag genuine stalls (ignoring routine deloads) and renders a color‑coded barbell sleeve graphic showing exact plates to load.

Источник

Hands‑Free Audio Briefing: Synthesizes a 10‑second voice recap via ElevenLabs (with offline browser speech fallback) straight into his gym earbuds.

Источник

Data Sovereignty: Workout logs, bodyweight, and personal notes stay in a local SQLite database (data/liftcast.db). Zero cloud egress.

Источник