Second
meeting notes you and your AI can actually use
What it does
There are plenty of good meeting note apps. Most of them pile on AI features and keep your notes inside their own cloud. Second does less. It records the call on your Mac, transcribes locally, and saves everything as markdown. Speaker labels, custom vocabulary, editable transcripts and persistent memory. Then a CLI and an MCP hand all of that to Claude, Codex or Hermes, so the meeting shows up inside the workflow you already have. $19 once. No subscription.
Private meeting memory for the AI tools you already use.
Second records calls on your Mac, writes private markdown notes, and gives Claude and Codex a local CLI for prep, follow-ups, and relationship history. Second captures the meeting cleanly, then gets out of the way. You get speaker-labeled transcripts, editable notes, custom vocabulary, audio playback, and markdown your agents can use. Second CLI, Codex plugin, and adaptive vocabulary should stay as product terms. After the call, the agent can draft the partner update and prepare the next review. Let’s keep the transcript editable so names and speaker labels can be fixed after processing. The raw notes should stay local and be easy for agents to read without another dashboard. I’ll send the…from getsecond.app
Does the same job
all alternatives →
More work this month
the category →
The app store for voice native apps that lives in your notch
Work · 28d ago · voiceos.com
The New Calendly▲211Handle all of the work before, during, and after meetings
Work · 17d ago · calendly.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com