Skip to main content

A self-hosted, Telegram-first AI assistant for productivity.

Project description

Gabay AI Assistant

Gabay is a self-hosted, Docker-based AI assistant designed as a Telegram-first productivity tool. It acts as a unified gateway allowing users to manage Gmail, Google Drive, Notion, and Meta (Facebook/Instagram) properties autonomously.

Features

  • Daily Briefing (/brief): Scans unread emails and Facebook/Instagram notifications to provide a prioritized, LLM-summarized update.
  • Content Reading (/read): Fetches unread emails and recent Notion pages (try "read my emails" or "what's new in Notion?").
  • Universal Search (/search): Deep-search across Google Drive and Notion directly from Telegram.
  • Seamless Saving: Reply to any file or PDF with /save to upload it to Drive or save to Notion.
  • Agentic Intent: Leverages Groq (Llama 3) to understand natural language requests.

Quick Install

Gabay is now available as a Python package. You can install it directly via pip:

pip install gabay

Then run the setup wizard:

gabay config

Setup Instructions (Docker)

Gabay uses both a Bot (commands) and a Userbot (acting as you).

  1. Bot: Create a bot via @BotFather to get your TELEGRAM_BOT_TOKEN.
  2. API Credentials: Go to my.telegram.org, log in, and create an "App" to get your TELEGRAM_API_ID and TELEGRAM_API_HASH.
  3. Phone Number: Your TELEGRAM_PHONE is required to authenticate the Userbot session.

2. Google Cloud Setup (Gmail/Drive)

  1. Go to the Google Cloud Console.
  2. Enable APIs: Enable both the Gmail API and Google Drive API.
  3. OAuth Consent Screen:
    • Set up an "External" consent screen.
    • Under Test Users, add your own email address.
  4. Create Credentials:
    • Create an OAuth client ID (Web application).
    • Add http://localhost:8000/auth/google/callback to Authorized redirect URIs.
  5. Get your Client ID and Client Secret.

3. Notion Setup

  1. Create an Internal Integration: Go to Notion My Integrations.
  2. Get your NOTION_API_KEY.
  3. Share Database: Open your Notion database, click "..." -> Connect to, and find your integration.
  4. Copy the Database ID from the URL (the string after the / and before the ?).

4. Environment Variables

Create a .env file in the root directory:

# Telegram
TELEGRAM_BOT_TOKEN="your_token"
TELEGRAM_API_ID=12345
TELEGRAM_API_HASH="your_hash"
TELEGRAM_PHONE="+123456789"

# LLM
GROQ_API_KEY="your_groq_key"

# Google OAuth
GOOGLE_CLIENT_ID="your_google_id"
GOOGLE_CLIENT_SECRET="your_google_secret"

# Notion
NOTION_API_KEY="your_notion_key"
NOTION_DATABASE_ID="your_database_id"

5. Running and Connecting

  1. Start: docker-compose up -d --build
  2. Dashboard: Send /auth to your bot on Telegram.
  3. Login: Open the link and click Connect Account for each service.

Use Cases

  • "Give me a briefing on my emails today."
  • "Read my latest Notion notes."
  • "Search for 'Project Alpha' on Drive."
  • "Send an email to john@example.com saying I'll be late."

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gabay-0.1.5.tar.gz (45.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

gabay-0.1.5-py3-none-any.whl (66.5 kB view details)

Uploaded Python 3

File details

Details for the file gabay-0.1.5.tar.gz.

File metadata

  • Download URL: gabay-0.1.5.tar.gz
  • Upload date:
  • Size: 45.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for gabay-0.1.5.tar.gz
Algorithm Hash digest
SHA256 69d747e8ce41365552abb63c1ca86566669631fec1e254191ec206fbf076f99a
MD5 41ccaf67d63184f76cb61ad33719e8be
BLAKE2b-256 7b92f6b6c5192b27860b7d91f0b2159cdd3174181a3d213a04f67e7425dad6f7

See more details on using hashes here.

Provenance

The following attestation bundles were made for gabay-0.1.5.tar.gz:

Publisher: pypi_publish.yml on urkiddennn/Gabay

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file gabay-0.1.5-py3-none-any.whl.

File metadata

  • Download URL: gabay-0.1.5-py3-none-any.whl
  • Upload date:
  • Size: 66.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for gabay-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 d63533be68cd4a97440fcb562160b7b5e567b8d054acd20a63dd5eacaef5f6b6
MD5 8bf4ed1e5de216b4bbd311997034143d
BLAKE2b-256 1d3db98aec7202c6a80cdb4587995f843eda30a5b9b1ada85dd648f834eb1a72

See more details on using hashes here.

Provenance

The following attestation bundles were made for gabay-0.1.5-py3-none-any.whl:

Publisher: pypi_publish.yml on urkiddennn/Gabay

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page