Ayush Gupta Posted on May 30 Building a Free OSHA Compliance Tool — 8 Weeks Solo # aws # machinelearning # python # opensource Commercial workplace-safety software — Protex AI, Intenseye, and the rest — runs $500 to $2,000 a month. It watches camera feeds for PPE violations: a worker without a hard hat, a missing high-vis vest, no fall harness at height. The technology isn't exotic anymore. The price tag is. So over eight weeks, solo, I built SafetyVision — an open-source PPE compliance monitor that does the core job for free and runs on $0 of infrastructure. Not a toy: a fine-tuned detection model, explainable predictions, OSHA-grounded incident reports, compliance forecasting, a documented API and SDK, and a one-command self-host. Three live surfaces, all free-tier. ▶ 3-minute walkthrough · Live app · GitHub This is the story of the decisions that mattered — including the ones that didn't go to plan. The product, in one breath Upload a worksite photo. SafetyVision finds each worker, flags missing PPE in red ranked by risk, shows you why it flagged it (a GradCAM heatmap and SHAP attribution), writes an incident report citing the actual OSHA regulation, exports an audit-ready PDF, and forecasts the site's 7-day compliance trend. Every inspection is saved to your history. It runs three ways: a Next.js web app on Vercel (the product), a no-signup Gradio demo on Hugging Face Spaces (the open-source try-it), and a serverless REST API on AWS Lambda (for developers). Same core powers all three. The compromises in this project are about scale — free tiers, a small model, a modest training set — never about sophistication . Here's where the sophistication went. The model: and an honest 0.763 Detection is a fine-tuned YOLOv8, exported to ONNX so it runs on a plain CPU — no GPU required for end users. Version 1 was YOLOv8* n * (nano), trained on ~58k images, landing at 0.701 mAP@50 . Decent, but it had a clear weakness: it was biased toward frontal poses and missed workers se
LIVE