DealForge autonomously sources, scores, and writes investment memos on venture deals. Stop manually hunting.
1,180+ deals tracked · 22 AI investment memos · Updated daily
Show HN: Agent Arnold – Gym tracker 100% vibe-coded from my phone between sets
Agent Arnold is a gym tracker with a built-in AI coach. Here's how I use it:<p>- "this exercise hurts my shoulder at the end of the movement, remind me proper form and cues"<p>- "how should I modify my workout today based off last week's reps and weights"<p>- `/generate` a bouldering-focused workout routine<p>The app is free, your data is fully exportable (no walled-gardens), and there's an anonymous global leaderboard for motivation, including a "Dishonored" shameboard for anyone caught faking their numbers.<p>I decided to 100% vibe-code this project, a part of it is halluci-coded. I purposely haven't touched a single line of code, though I've reviewed most of it. The project started as just my own workout split, but friends wanted to try it so I added routines, then feature requests started coming in and I basically just forwarded them to my CLI agents.<p>Vibe-coding is far from perfect, but since I'm a daily user of my own app I catch bugs immediately, sometimes literally in the gym while SSHing from my phone between sets.<p>---<p>Tech stack: - FastAPI + SQLite on a Linux box - React PWA (works offline) - AI coach powered by Claude via Anthropic API - Telegram OAuth + Resend magic-link auth - Sentry for error tracking, Foursquare Places for gym location<p>The whole thing was built with Claude Code. Vibe-coded with Claude, and the AI coach is also Claude. It's Claude all the way down.<p><a href="https://agent-arnold.app/" rel="nofollow">https://agent-arnold.app/</a><p>---<p>What do you hate about your current fitness tracker? I might fix that.
Agent Arnold is a compelling proof-of-concept for AI-native fitness tracking, but it currently lacks a business model, technical moat, or proven scalability. While the 'vibe-coding' approach demonstrates impressive speed-to-market and founder-market fit, the reliance on unreviewed AI code and a crowded competitive landscape present significant long-term investment risks.