Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

Wisprnote

Open-source AI meeting OS that never joins your call

Details

External ID
1256904
Source
PH
Company
—
Product
Wisprnote
Website domain
producthunt.com
Launched
Sept. 23, 2026
Cohort
—
Upvotes
2
Upvotes percentile
0.7405388069275176
Tags
Meetings, GitHub, Audio
Fetched at
Sept. 25, 2026, 1:01 a.m.
Updated at
Sept. 25, 2026, 1:01 a.m.

Description

Wisprnote turns meetings into execution — and it runs on your Mac, not someone else's cloud. It hears your mic and your system audio, so nothing joins the call — it works in Zoom, Meet and Teams. Every meeting becomes a summary, decisions and action items, then joins a knowledge graph across everything you've recorded. A built-in MCP server lets Claude and Cursor read that knowledge directly. Connectors turn action items into Jira tickets, with you approving each step. Open source, AGPL-3.0.

Enrichment

Theme
AI voice recorders and meeting notetakers
Vertical
Horizontal
Function
Workflow automation
Audience
Prosumer
AI stance
AI-native
Project type
Hobby / open-source project
Normalized one-liner
open-source ai meeting recorder for professionals
Manually corrected
False

Could you build this?

Partial Building a macOS app that captures system-level audio loops without virtual drivers, runs local speech-to-text models like Whisper, and constructs a contextual knowledge graph requires deep native OS audio engineering.

What it would actually take: The product requires a native macOS app (Swift/Objective-C) integrating Apple's ScreenCaptureKit or CoreAudio HAL taps to capture multi-channel system audio and microphone streams cleanly without bot interception. The system then needs a high-throughput, low-latency audio pipeline feeding into local Whisper models (via whisper.cpp or MLX), followed by an LLM-driven graph extraction engine storing nodes and edges in a local graph database (e.g., Kùzu or SQLite). The hard parts are seamless desktop audio interception permissions and low-latency on-device multi-speaker transcription.

Competitors

Other products that read as similar to this one — 57 launches clear the similarity bar, closest 8 shown.

Attention rank: #21 of 58 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 267 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a workflow automation tool for Real estate yet.