RUNFORM
AI scores your running form across 7 biomechanical metrics
RUNFORM launched on May 20, 2026 with 1 votes.
What it does
RUNFORM analyzes your running form from a smartphone video using Google MediaPipe AI — no installation, works in any browser. 7 metrics scored instantly: • Trunk Lean • Knee Drive • Arm Swing • Landing Position • Knee Flexion • Vertical Oscillation • Cadence Each rated GOOD / OK / NG with coaching advice. Goal-based feedback adapts for sprint, middle, or long distance. ✅ Free, no sign-up required 📱 iOS / Android / Desktop 🌐 Japanese & English 💾 Save & track progress
スマホで撮った走り動画をAIが解析。体幹前傾・膝引き上げ・ケイデンスなど7項目をスコア採点してアドバイス。無料・登録不要でブラウザだけで完結。
RUNFORM uses AI to analyze your running technique from a smartphone video. 7 biomechanical metrics are scored and rated GOOD / OK / NG — no coaching experience required. Free, no installation, works in anyfrom itsapieceofcake4-max.github.io
Does a similar job
all alternatives →
Running Form Analysis App Dec 2025 · fruitfoxlu.github.io · ▲80Upload a short side-view clip, get actionable form feedback


Vitesse Running: AI tracking2020 · vitesserunning.com · ▲70Take running to the next level with custom interval workouts

AI Running Trainer2024 · apps.apple.com · ▲6AI-powered runningcoach for personalized training & feedback
More ai this month
the category →



Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video

Source: Product Hunt launch ↗
Launched alongside, May 2026
the whole month →

Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai



Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com

🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com