convez.ai
MCP ServerProdutividadeAvançado
addicted-studio

Daisy App

addicted-studio/daisy-app

Gravador de reuniões privado para Mac com transcrição Whisper e resumos via Claude

Ver no GitHub
BomPluginScore · de 0 a 100

Gravador de reuniões local-first para macOS que transcreve áudio on-device com Whisper e gera resumos com IA. Integra-se ao Claude Desktop via MCP server, mantendo áudio privado na máquina do usuário até que ele opte por usar provedores cloud com sua própria chave de API.

Instalação

$npx convez-ai addicted-studio/daisy-app

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
18
Forks
4
Acompanhando
2
Saúde
100%
Último commit
há 2 dias
Versão
v1.0.8.51
Issues abertas
0
Contribuidores
1

Casos de uso

  • Registrar e transcrever reuniões sem enviar áudio para a nuvem
  • Gerar automaticamente resumos e itens de ação com IA
  • Integrar transcrições e resumos ao fluxo de trabalho do Claude Desktop

Veredito

Daisy é uma solução robusta e bem-arquitetada para captura e resumo de reuniões com foco em privacidade. A integração MCP com Claude Desktop e o suporte a múltiplos provedores de resumo (Apple Intelligence, Anthropic, OpenAI) a tornam flexível, mas exige macOS 14+ e conhecimento técnico para build from source.

README

A tradução para o português deste README ainda está na fila.

Daisy

A local-first meeting recorder and AI notes app for macOS.

Daisy captures meeting audio (microphone + system audio loopback via ScreenCaptureKit), transcribes it on-device with Whisper, and produces a Granola-style outline with action items and a draft client follow-up. Audio never leaves the Mac unless the user explicitly enables a cloud LLM provider (Anthropic / OpenAI / MCP) for the summary step — and even then the user supplies their own API key.

End-user installation, FAQ, and the privacy story live at https://mydaisy.io. This README is for people building Daisy from source.

Status

  • Latest stable release: see scripts/release-notes/ and https://mydaisy.io/appcast.xml
  • Deployment target: macOS 14 Sonoma (Apple Intelligence summarizer requires macOS 26 Tahoe)
  • Apple Silicon and Intel x86_64 universal binary
  • Signed with Developer ID, notarized, stapled, Sparkle EdDSA-signed for in-app updates

Build from source

Requirements:

  • Xcode 16+ with the macOS 26 SDK installed
  • An active Apple Developer account if you want to run a signed local build (unsigned builds are fine for development inside Xcode)

Clone and open:

git clone https://github.com/addicted-studio/daisy-app.git
cd daisy-app
open Daisy.xcodeproj

The Swift Package Manager dependencies (Sparkle, WhisperKit/ArgmaxCore, FluidAudio) resolve on first project load. Hit Run; the app launches.

Project layout

Daisy/                  → SwiftUI app sources (PBXFileSystemSynchronizedRootGroup)
DaisyTests/             → unit tests
DaisyUITests/           → UI tests
Daisy.xcodeproj/        → Xcode project
scripts/
  release.sh            → end-to-end release: archive → notarize → DMG → sign → Sparkle appcast
  release-notes/        → per-version markdown bullets consumed by release.sh
  dmgbuild_settings.py  → dmgbuild config (Python) for the installer DMG
  assets/               → DMG background, app icons
build/                  → archive output (gitignored)

Key services that drive the app:

  • AudioRecorder — AVAudioEngine mic tap, route-change recovery, archive .caf writer
  • SystemAudioCapture — SCStream loopback for the remote side of a meeting, BT-output detection, silent-capture warnings
  • Transcriber — WhisperKit on-device transcription with Silero VAD pre-pass
  • RecordingSession — orchestrates a session, owns calendar binding and auto-stop scheduling
  • Summarizer — multi-provider cloud / on-device LLM dispatch (Apple Intelligence, Anthropic, OpenAI, MCP)
  • SparkleUpdater — wraps Sparkle 2 against https://mydaisy.io/appcast.xml

Release flow

DAISY_AUTO_PUSH=1 ./scripts/release.sh <shortVersion> <buildNumber>

Six steps: archive → export → notarize → DMG → publish to the daisy-web repo → inject an <item> into appcast.xml and commit. Vercel auto-deploys the site within a couple of minutes.

Release notes for each version go in scripts/release-notes/<shortVersion>.md as a flat markdown bullet list (- one line per change). The script extracts those bullets and embeds them in the appcast <description> so Sparkle shows them in its update sheet.

Support and contact

Credits

License

See LICENSE.

Ver o original no GitHub

Bom para

Relacionados