Skip to main content

AI Personal Agent SDK

A comprehensive, secure AI-powered personal assistant SDK that provides 24/7 automation, intelligent planning, and beautiful web interface for managing your digital life.

Features

🤖 AI-Powered Automation

  • Intelligent Planning: Daily schedule optimization using OpenAI GPT-4
  • Smart Reminders: Context-aware notifications for meetings and tasks
  • Conversational AI: Natural language chat interface for assistance

🔒 Enterprise-Grade Security

  • End-to-End Encryption: All data encrypted with AES-256
  • Permission-Based Access: Granular control over data access with time-limited permissions
  • Hacker Protection: Continuous monitoring and security alerts
  • Local Data Storage: No data sent to external servers without explicit permission

🔗 Seamless Integrations

  • Google Services: Gmail, Google Calendar integration
  • Zapier Automation: Connect with 5000+ apps and services
  • Social Media: Automated posting and monitoring
  • Email Management: Intelligent email processing and responses

🎨 Beautiful Web UI

  • Responsive Design: Works on desktop, tablet, and mobile
  • Real-time Dashboard: Live updates of meetings, tasks, and alerts
  • Interactive Chat: AI assistant with natural conversation
  • Permission Management: Visual approval system for data access

📱 24/7 Monitoring

  • Continuous Operation: Background monitoring of all data sources
  • System Health: Resource usage and performance monitoring
  • Security Alerts: Instant notifications for security events
  • Data Integrity: Automatic corruption detection and repair

Architecture

┌─────────────────┐    ┌─────────────────┐    ┌─────────────────┐
│   Web UI        │    │   Core Agent    │    │   Integrations  │
│   (Flask)       │◄──►│   (Scheduler)   │◄──►│   (Google,      │
│                 │    │                 │    │    Zapier)      │
└─────────────────┘    └─────────────────┘    └─────────────────┘
         │                       │                       │
         ▼                       ▼                       ▼
┌─────────────────┐    ┌─────────────────┐    ┌─────────────────┐
│   Security      │    │   Monitoring    │    │   Data Storage  │
│   (Encryption,  │    │   (24/7 Health  │    │   (Encrypted    │
│    Permissions) │    │    Checks)      │    │    Local)       │
└─────────────────┘    └─────────────────┘    └─────────────────┘

Core Components

  1. PersonalAgent: Main orchestrator class
  2. Security Layer: Encryption and permission management
  3. Integration Layer: External service connections
  4. Monitoring System: Continuous health and security checks
  5. Web UI: User interface and API endpoints

Installation

Prerequisites

  • Python 3.8+
  • OpenAI API key
  • Google Cloud Project (for Google integrations)
  • Zapier API key (optional, for advanced automations)

Install from Source

git clone https://github.com/yourusername/ai-personal-agent-sdk.git
cd ai-personal-agent-sdk
pip install -e .

Install Dependencies

pip install -r requirements.txt

Quick Start

1. Environment Setup

Create a .env file in your project directory:

# Required
OPENAI_API_KEY=your_openai_api_key_here

# Optional - for Google integrations
GOOGLE_CREDENTIALS_PATH=path/to/google/credentials.json

# Optional - for Zapier automations
ZAPIER_API_KEY=your_zapier_api_key_here

# Optional - custom settings
DATA_STORAGE_PATH=./my_agent_data
UI_PORT=8080
MONITORING_INTERVAL=60

2. Google Setup (Optional)

  1. Go to Google Cloud Console
  2. Create a new project or select existing one
  3. Enable Gmail API and Google Calendar API
  4. Create credentials (OAuth 2.0 Client ID)
  5. Download the credentials JSON file
  6. Set the path in your .env file

3. Basic Usage

from ai_personal_agent_sdk import PersonalAgent, Config

# Load configuration
config = Config()

# Create agent
agent_config = Config.AgentConfig(
    openai_api_key=config.openai_api_key,
    zapier_api_key=config.zapier_api_key,
    google_credentials_path=config.google_credentials_path
)

# Start the agent
agent = PersonalAgent(agent_config)
agent.start()

# The web UI will be available at http://localhost:8080

4. Using the Web Interface

  1. Open your browser and go to http://localhost:8080
  2. View your dashboard with meetings, daily plan, and active permissions
  3. Chat with the AI assistant
  4. Set alarms and manage automations
  5. Approve or deny permission requests

API Reference

PersonalAgent Class

Initialization

agent = PersonalAgent(config: AgentConfig)

Methods

  • start(): Start the agent and all services
  • stop(): Stop the agent and save data
  • request_permission(action, resource, duration_minutes): Request permission for an action
  • execute_automation(type, params): Execute automation via Zapier
  • get_meetings(): Get upcoming meetings
  • add_alarm(time, message): Add a new alarm
  • get_daily_plan(): Get today's AI-generated plan

Security Features

Data Encryption

All sensitive data is automatically encrypted using AES-256 encryption:

from ai_personal_agent_sdk.security import DataEncryptor

encryptor = DataEncryptor(key)
encrypted = encryptor.encrypt(b"sensitive data")
decrypted = encryptor.decrypt(encrypted)

Permission Management

from ai_personal_agent_sdk.security import PermissionManager

pm = PermissionManager()
approved = pm.request_permission("read_email", "gmail", 60)  # 60 minutes

Integrations

Google Services

from ai_personal_agent_sdk.integrations import GoogleIntegration

google = GoogleIntegration("path/to/credentials.json")
emails = google.get_recent_emails()
events = google.get_today_events()

Zapier Automations

from ai_personal_agent_sdk.integrations import ZapierIntegration

zapier = ZapierIntegration("your_api_key")
result = zapier.execute_automation("email_reply", {"message": "Hello!"})

Security Best Practices

Data Protection

  • All data is stored locally and encrypted
  • No data is sent to external servers without explicit permission
  • Encryption keys are managed securely

Permission System

  • All sensitive operations require explicit permission
  • Permissions are time-limited and auto-expire
  • Users can revoke permissions at any time

Network Security

  • All API calls use HTTPS
  • Credentials are stored encrypted
  • No sensitive data in logs

Monitoring & Alerts

  • Continuous security monitoring
  • Instant alerts for suspicious activity
  • Regular data integrity checks

Configuration Options

Variable Description Default
OPENAI_API_KEY OpenAI API key Required
ZAPIER_API_KEY Zapier API key Optional
GOOGLE_CREDENTIALS_PATH Path to Google credentials Optional
DATA_STORAGE_PATH Data storage directory ./agent_data
UI_PORT Web UI port 8080
MONITORING_INTERVAL Monitoring check interval (seconds) 60

Troubleshooting

Common Issues

  1. OpenAI API Key Issues

    • Ensure your API key is valid and has sufficient credits
    • Check the key format (should start with sk-)
  2. Google Integration Problems

    • Verify credentials JSON file path
    • Ensure APIs are enabled in Google Cloud Console
    • Check OAuth consent screen configuration
  3. Permission Denied Errors

    • Check if the required permissions are granted
    • Verify permission expiration times
    • Look for pending permission requests in the UI
  4. Web UI Not Loading

    • Check if port 8080 is available
    • Verify Flask is installed correctly
    • Check browser console for JavaScript errors

Logs and Debugging

Enable debug logging:

import logging
logging.basicConfig(level=logging.DEBUG)

Check the logs for detailed error information and system status.

Contributing

We welcome contributions! Please see our Contributing Guide for details.

Development Setup

git clone https://github.com/yourusername/ai-personal-agent-sdk.git
cd ai-personal-agent-sdk
pip install -e ".[dev]"

Running Tests

pytest tests/

License

This project is licensed under the MIT License - see the LICENSE file for details.

Support

Roadmap

  • Mobile app companion
  • Voice interface integration
  • Advanced AI models support
  • Multi-user support
  • Plugin system for custom integrations
  • Advanced analytics and insights

Important Security Notice: This SDK is designed with privacy and security as top priorities. All data processing happens locally on your device. No personal data is transmitted to external servers without your explicit permission and approval.

Release files for ai-personal-agent-sdk 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ai-personal-agent-sdk 0.1.0
File Size Uploaded
ai_personal_agent_sdk-0.1.0.tar.gz 24.0 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for ai-personal-agent-sdk 0.1.0
File Interpreter ABI Platform
ai_personal_agent_sdk-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 46.8 kB

Release files / ai_personal_agent_sdk-0.1.0.tar.gz

Download URL ai_personal_agent_sdk-0.1.0.tar.gz
Size 24.0 kB
Tags Source
SHA-256 checksum
How to use checksums
a5fe71ef13a8c30c2d7037f0ecb9305f558ba9c682709b9dfef3a39ac6ffe4f3
BLAKE2b-256 checksum
How to use checksums
b28bbb14789266e5501ff05022d5125c6e7a7d1a020f787ca4b3240d4026c518
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.10

Release files / ai_personal_agent_sdk-0.1.0-py3-none-any.whl

Download URL ai_personal_agent_sdk-0.1.0-py3-none-any.whl
Size 22.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
f38a9d0a904be72470d62fcee327b80d60851222cd2ccc9eb8853136eb04f913
BLAKE2b-256 checksum
How to use checksums
857256903e5d0fc5cbf92571084253c0f053302093b99980371bad624638cb6e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.10

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page