Gemma Gem vs Onboarding0

Gemma Gem is an open-source Chrome extension that runs Google's Gemma 4 language model entirely in your browser using WebGPU — no API keys, no server, no data leaving your device. Install the extension, wait for the one-time model download (500MB for the efficient 2B variant, 1.5GB for the larger 4B), and you have a fully private AI assistant that can read web pages, fill forms, take screenshots, and execute JavaScript. The extension uses Hugging Face Transformers.js with ONNX-quantized versions of Gemma 4's E2B and E4B variants, making the model small enough to run in a browser tab without throttling GPU memory. Gemma 4's strong efficiency profile — particularly its per-layer attention architecture — makes it a natural fit for WebGPU's memory constraints compared to older models at similar parameter counts. What makes Gemma Gem interesting beyond the cool factor: it's a glimpse at what fully private, zero-latency browser-native AI looks like. There's no round-trip to a server, no API billing, no rate limits. On a mid-range MacBook M3 or gaming GPU, inference is fast enough to be genuinely useful. The trade-off is capability — Gemma 4 E2B is a 2B parameter model, not Claude or GPT-5, but for summarization, form-filling, and basic Q&A it holds its own.

Onboarding0 is an AI agent that transforms a company's scattered documentation and organizational knowledge into a structured, personalized onboarding experience for new hires. Built by Leon Arnovitz (former VP of Engineering), the tool connects to existing docs, maps the org structure, and then deploys an AI agent that guides each new employee to productivity — replacing the patchwork of wikis, Slack DMs, and first-day confusion that plagues most companies. The core insight is that onboarding failure is usually a knowledge retrieval problem, not a motivation problem. New hires spend weeks hunting for the right person to ask or the right document to read. Onboarding0's agent knows the entire knowledge graph upfront and serves answers proactively, adapting to each hire's role and department. Onboarding0 is currently free, which makes it an easy experiment for any startup or mid-size company tired of watching expensive new hires flounder in week one. The agentic approach distinguishes it from static wikis like Confluence or Notion — the agent asks follow-up questions, routes to the right person when it hits the edges of its knowledge, and tracks what each new hire has actually understood.