AI meeting notes with transcripts, speaker recognition, summaries, decisions and action items. Record, upload or capture calls, and sync to Slack and Notion.
ProductivityTypeScript · JavaScriptGitHub @NiyioxyOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
No updates detected yet. GitHub releases will appear here.
GitHub star growth between the latest completed 8-hour observations
DeepSeek Harness Remote can securely connect a phone or another computer to the computer where you run DeepSeek Harness, so you can continue your work anytime and anywhere, check progress anytime, and continue working.
AI translation
Automate with computer-use agent (ComputerUse / CUA) for macOS, Windows, Linux, Browser, iOS & Android. It sees the screen, clicks, types, browses and writes the code too. One agent, every computer.
Hide the menu bar icons you don't need behind a chevron and bring them back the instant you ask. Native, private, free for macOS.
Independent open-source file toolkit inspired by Tangerine, with added web downloads, QR reading and editing workflows. / Tangerine’den ilham alan, yeni özelliklerle geliştirilen bağımsız açık kaynak
Translation pending
Fold papers, web pages, files, and AI replies into five levels of detail. Zoom from an overview to the original text.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
Meeting Intelligence automated
Translation pending
Taken from the repository README
Loading the full README.
Read the full README ↗AI meeting intelligence: upload or record a meeting, get a transcript (Deepgram), and a summary, action items, decisions, open questions, and sentiment (Gemini).
Next.js 14 (App Router) · Neon Postgres · Drizzle ORM · NextAuth.js (Auth.js v5, Google OAuth) · Deepgram + Gemini · Tailwind CSS v4 + shadcn/ui
Install dependencies (already done if you're reading this from the generated project):
npm install
Create a Neon database at neon.tech and copy its connection string.
Create a Google OAuth client at the Google Cloud Console:
http://localhost:3000/api/auth/callback/google (and your production URL equivalent)Copy .env.example to .env.local and fill in real values:
cp .env.example .env.local
DATABASE_URL — Neon connection stringNEXTAUTH_SECRET — generate with openssl rand -base64 32NEXTAUTH_URL — http://localhost:3000 locallyGOOGLE_CLIENT_ID / GOOGLE_CLIENT_SECRET — from step 3DEEPGRAM_API_KEY — from console.deepgram.comGEMINI_API_KEY — from aistudio.google.com/apikeyPush the schema to Neon:
npm run db:migrate
(A migration is already generated at drizzle/0000_massive_johnny_storm.sql. db:migrate applies it. Use npm run db:generate after future schema changes, and npm run db:studio to browse data.)
Run the dev server:
npm run dev
Speaker voice recognition (enrolment + identification) runs through a
self-hosted Python microservice at voice-service/ using
SpeechBrain's ECAPA-TDNN speaker embedding model — no API keys or usage
limits. It must be running alongside the Next.js app in dev for voice
enrolment/identification to work; without it, those features fail closed
(the app still works, meetings just fall back to Gemini's speaker guesses).
Set up once:
cd voice-service
python -m venv .venv
.venv\Scripts\activate # or `source .venv/bin/activate` on macOS/Linux
pip install -r requirements.txt
Requires the ffmpeg binary on your PATH (used to normalize uploaded audio
before embedding).
Then, side by side with npm run dev, run:
npm run voice-service
which starts uvicorn main:app --port 8001 --reload. Set
VOICE_SERVICE_URL in .env.local (defaults to http://localhost:8001,
see .env.example) so the Next.js app knows where to reach it.
/api/meetings/upload and /api/meetings/analyze can take a while for long meetings — both routes are configured with maxDuration = 300. On Vercel, this requires a plan that supports extended function durations.