TL;DR: open-source desktop dictation app that sits next to every AI chat window you have open. Local Whisper for speech-to-text. Wake-word listening so you don't even click. Optional AI parse via Ollama, OpenAI, or Anthropic. MIT, free, no telemetry. 🔗 GitHub: https://github.com/Agenius-AI-Labs/agenius-note 🔗 PyPI: pip install agenius-note 🔗 Walkthrough video: https://youtu.be/OAcrm0wZd6Y The problem it solves I usually have three Claude windows, a VS Code Claude session, ChatGPT, and a local Ollama open at the same time. Every prompt I type is a context-switch tax. The Whisper-based dictation built into macOS / Windows works but lives in the OS chrome, not next to my chats. Claude Desktop has voice but it's tied to Claude. I wanted one mic for everything. What it does 🎙 Push-to-talk dictation, or hands-free wake word (default "hey jarvis", train your own .onnx in the openWakeWord Colab notebook) 🧠 Pipes the transcript to your LLM of choice for a structured note/task parse. Or skip the LLM and just take raw transcripts ✅ Quick todos pane on the right ("hey jarvis, remind me to walk the dogs in an hour" routes straight in) 📋 Quick Note brain-dump panel. Talk a thought through, hit Copy, paste into your next prompt. Nothing stored 🔐 API keys live in OS keyring (Keychain / Credential Manager / Secret Service). No plaintext on disk Stack PySide6, faster-whisper (CUDA float16 with CPU fallback), openWakeWord, SQLite, Ollama / OpenAI / Anthropic. ~5K LOC. MIT license. It runs everywhere Windows, macOS, Linux. Pre-built bundles on the GitHub Releases page (SmartScreen and Gatekeeper will yell on first launch, we're not code-signed yet). Or pip install agenius-note if you have Python 3.10+. What I'd love feedback on - What wake word would you train (mine is going to be "hey biggie" once I get around to it) - Which LLM backend feels best for your workflow - What's missing (next on my list: a chat panel inside Quick Note so I can ask the AI things without leaving the app)

I’m 46. I spent 30 years on the tools. I joined Nate’s AIS Skool community in October last year. This morning a UK construction MD emailed me four words I’ll remember for the rest of my life: “Can we proceed with phase-1 please.” Here’s how it happened. Today, the MD of a UK construction firm emailed me four words I’ll remember for the rest of my life. “Can we proceed with phase-1 please.” £4,500 Phase 1 build. 50% deposit on start, 50% on delivery, two-week go-live guarantee. Signed verbally Tuesday evening, confirmed in writing this morning. This is not a victory lap. This is a story for anyone in this community sitting where I was sitting back in October when I first showed up. If I can do this, you absolutely can. Here’s how it actually happened. Where I came from 30 years on the tools. 20 of them co-founding a construction firm that grew from 2 people to 70. I’m 46. I started teaching myself AI in early 2025. Properly self-taught. No degree, no tech background, just YouTube and reading and breaking things and fixing them. The timeline that matters for this room: - 23 June 2025 I joined Liam Ottley’s AAA Skool community. Still a member today. - 15 September 2025 I incorporated ConstructionX AI Ltd at Companies House. - October 2025 I joined Nate Herk’s AIS Skool community. - November 2025 I joined AIS+. - Late January 2026 I stepped up into Liam’s paid AAA Accelerator tier. Still a member today. - 13 February 2026 the workspace went live and I committed to two posts a day. - 14 May 2026 (today) the first £4,500 build signs through the productised funnel. The brand had been quietly forming for months before the daily build started. Domain registered, soft conversations, early demos for friends. The visible push did not really begin until February. So: - ~14 months teaching myself AI - 8 months since incorporation - 7 months in this room - 6 months in AIS+ - 3 months of daily public building - Today, the first £4,500 build Not slowly, not quickly. Just relentlessly.