humanitas-labs/quill

Ultra-minimalist macOS recording + transcription.

What it solves

Quill provides a private, local-first approach to meeting recording and transcription. It eliminates the need to send audio data to cloud services, ensuring that meeting recordings and their corresponding transcripts remain entirely on the user's machine.

How it works

The application records microphone input and system audio (the call's audio) as separate tracks. Once the recording is stopped, it performs on-device transcription to generate a timestamped transcript that distinguishes between the speaker (me) and the other participants (them).

Who it’s for

Users on macOS 15+ (specifically those with Apple Silicon for better performance) who need to secure their meeting recordings and transcripts by keeping them local.

Highlights

  • Local-first: All audio capture and transcription happen on-device.
  • Dual-track recording: Captures both the microphone and the call audio separately.
  • Separate speaker identification: Produces transcripts formatted as me / them.
  • Native implementation: Built as a native application for macOS, with plans for Windows and Linux.

Related

  • Project
    nicobailon/pi-subagents

    pi‑subagents is a Pi AI‑assistant extension that lets the main Pi session spawn focused child agents (scout, reviewer, worker, oracle, etc.) to handle tasks like code review, research, implementation, and auditing. Subagents can run in the foreground (streaming live) or in the background (detached process). Users simply install the package (`pi install npm:pi-subagents`) and then ask Pi in plain language (e.g., “Use reviewer to review this diff”). The system orchestrates the child agents, provides observability via a FleetView panel, and offers configuration options such as tool activation and spawn limits.

  • Project
    claraverse-space/ClaraVerse

    ClaraVerse is a private AI workspace focused on AI agent teams, layered memory, and a permissive license, offering chat, multi-agent collaboration, terminal agent, workflow automation, and 150+ integrations.

  • Project
    yuruotong1/autoMate

    autoMate is a locally hosted service that gives AI chat clients persistent personal storage (notes, files, reminders, long‑term memory) and a toolbox of real‑world actions (shell, browser, SaaS APIs). It talks to clients via an MCP‑over‑HTTP bridge, works with OpenClaw, Claude Desktop, Cursor, Cline, etc., and can also be used through its own web chat, Chrome extension, Docker container, or binary.

  • Project
    synthetic-sciences/openscience

    OpenScience is an open‑source AI research workbench that lets users describe scientific tasks in plain language. The built‑in agent plans, searches literature, writes and runs code (Python/R/shell), executes experiments on local or remote compute, and produces a reproducible report, with every step logged. Available as a desktop app, web workspace, or CLI, it supports custom LLMs, a large library of domain‑specific skills, and extensible plugins.