Hey Product Hunt! Ahead of our Dayglass Hypership launch tomorrow (Nov 6 at 12:01 AM PT), wanted to share the architecture behind why we built a 100% local, bot-free meeting & screen memory engine for macOS:
1. Zero creepy meeting bots: Instead of inviting an Otter/Fireflies/Fathom bot into your Zoom, Teams, or Meet calls, Dayglass captures system audio + mic + Apple Vision screen OCR natively on Apple Silicon.
2. Solving the 6 26 GB/user KV-cache context bottleneck: Revolut just revealed they cut AI coding costs 90% by making frontier Claude the exception, but hit a 6 26 GB/user GPU RAM bottleneck just for context retention. Dayglass stores a 3-layer Unified Context Graph (short_term, long_term, decision_trace) in <225 MB of local SQLite and exposes 26 MCP tools to Claude Desktop, Cursor, and Codex in <15ms.
Hey Product Hunt! 👋 I’m Igor, maker of Dayglass (https://dayglass.io).
In the shift from the Chatbot Era to the Agent Era, coding and workflow agents still fail for one boring reason: they lack context about you—while traditional meeting recorders force creepy bots (Otter, Fireflies, Read.ai) into your Zoom/Teams calls and upload confidential audio to someone else’s cloud.
Why we built Dayglass:
Zero meeting bots: Captures system audio + mic + screen OCR directly on your Mac (Apple Silicon native).
On-Device SQLite + MCP: Claude Desktop, Cursor, Codex, and OMP query your live meeting decisions, asks, and screen timeline in real time without cloud egress.
Governance as a feature: Tamper-evident HMAC-SHA256 Signed Memory Receipts for every captured engineering/product decision.
Pricing & Product Hunt Launch Offer:
Free forever: 5 meetings/week on your Mac.
Dayglass Pro ($19/mo) & Lifetime ($149): Unlimited meetings, live MCP agent streaming, and Obsidian dual-vault sync at https://dayglass.io (use code PRODUCTHUNT30 for 30% off!).