Agentfy

Agentfy is a modular, multi-agent coordination system designed to automate social media workflows using a flexible MCP (Model Context Protocol). It orchestrates multiple agents to reason, perceive, and act across platforms like TikTok, Instagram, YouTube, and X, enabling tasks such as buyer targeting, cross-platform promotions, content transformation, and automated messaging. After starting the server, you can interact with the CLI to trigger agent workflows or launch the Streamlit-based UI for a graphical interface. The system relies on your API keys and environment configurations to access social media services and OpenAI for reasoning and task planning. The included agents can be extended or customized by adding new sub-agents under the agents/ directory and updating the agent registry.

Prerequisites:

• Python 3.11+ installed on your machine
• Access keys for required platforms (OpenAI, X, YouTube, TikTok, Instagram, etc.)
• Git installed

Installation steps:

1. Clone the repository git clone https://github.com/callmeiks/Agentfy.git
2. Navigate to the project directory cd Agentfy
3. Create and configure a virtual environment (optional but recommended) python -m venv venv source venv/bin/activate # On Windows use: venv\Scripts\activate
4. Install Python dependencies pip install -r requirements.txt
5. Set up environment variables
   • Create a .env file or export variables in your shell, e.g.: export OPENAI_API_KEY=your_key_here export X_API_KEY=your_key_here export X_API_SECRET=your_secret_here export YOUTUBE_API_KEY=your_key_here
   • Ensure any platform-specific keys are present
6. Run the Agentfy CLI or UI (see next section)

Notes:

• If you modify agents, ensure they follow the existing directory structure and update agent_registry.json accordingly.

Tips and common issues:

• Ensure all required API keys are valid and have the necessary permissions for the actions you intend to perform (posting, DMs, data retrieval).
• If the MCP server cannot access external services, check network restrictions, firewall rules, and environment variable availability within the runtime environment.
• When adding new sub-agents, follow the documented registry format and test in CLI mode before switching to the UI to validate behavior.
• For debugging, set LOG_LEVEL to DEBUG in the environment to get verbose logs.
• If running locally, ensure the platform APIs you plan to use support your development environment and provide the correct redirect/Callback URLs where required.