Digital-FTE

Digital-FTE is an open-source autonomous AI agent system designed to act as a 24/7 digital employee, coordinating cloud and local capabilities to manage tasks like email handling, accounting, and social media actions. The system uses a dual-agent architecture: a Cloud Agent that monitors inputs (Gmail, LinkedIn, WhatsApp) and drafts proposals, and a Local Agent that runs on your machine to execute tasks once you approve them. MCP servers orchestrate the execution of tasks across tools and AI models, ensuring actions are only taken with human approval. With docker-compose support, you can deploy the entire stack with a single command, or run individual Python components for development and testing. The included test suite and guardians self-evolve the system by proposing patches to fixes and improvements in the Vault, subject to your approval.

Prerequisites:

• Python 3.10+
• Node.js 18+ (for potential frontend/tools in the ecosystem)
• Docker and Docker Compose (optional but recommended for one-command deployment)
• Git

1. Clone the repository:

git clone https://github.com/AbdullahMalik17/Digital-FTE.git
cd Digital-FTE

2. Create and activate a Python virtual environment (recommended):

python -m venv venv
# Windows
venv\Scripts\activate.bat
# macOS/Linux
source venv/bin/activate

3. Install Python dependencies:

pip install -r requirements.txt

4. Configure environment variables:

cp .env.example .env
# Edit .env and fill in API keys and credentials as described in the Configuration section of the README

5. Run the MCP components locally (development):

# Start the local agent (executor)
python src/local_agent.py

# In another terminal, start the watchers
python src/service_manager.py

6. Optional Docker deployment:

docker-compose up --build

Notes:

• For a full production-like setup, prefer Docker Compose to orchestrate both services and dependencies.
• Ensure your API keys and credentials in .env are valid before starting the system.

Tips and common issues:

• The Guardian/self-evolution feature requires proper error handling logs; check Logs/Audit for JSONL traces when something fails.
• Make sure GMAIL_CLIENT_ID/SECRET, ODOO credentials, and social media tokens are valid to avoid startup errors.
• When running locally, ensure the Vault directory is writable by the process to allow parallel read/write operations.
• If you encounter Python module import errors, verify you’re using the correct virtual environment and that dependencies in requirements.txt are up to date.
• Docker deployment simplifies environment parity across dev/stage/prod; use docker-compose to bring up all services with one command.