Agentfy  by Agentfy-io

Multi-agent system for social media automation

Created 10 months ago
378 stars

Top 75.6% on SourcePulse

GitHubView on GitHub
Project Summary

Agentfy is a modular, multi-agent system designed for automating social media tasks across platforms like TikTok, Instagram, and X. It leverages LLMs and a flexible Model Context Protocol (MCP) to translate user intents into executable workflows, enabling cross-platform promotions, content transformation, automated messaging, and creator discovery for users and businesses.

How It Works

Agentfy employs a modular microservices architecture with a focus on multi-agent coordination. It uses a Model Context Protocol (MCP) and LLMs to interpret user requests, breaking them down into structured tasks. The system supports dynamic agent communication and collaboration, automatically selecting and routing requests to the most suitable agents and functions without manual configuration, enabling intelligent workflow execution.

Quick Start & Requirements

  • Installation: Clone the repository (git clone https://github.com/callmeiks/Agentfy.git), navigate to the directory, and install dependencies via pip install -r requirements.txt.
  • Prerequisites: Requires API keys for platforms like OpenAI, X, YouTube, TikTok, etc., to be set in a .env file.
  • Running: Can be run via a Command Line Interface (python run_agent_cli.py) or a Streamlit Web Interface (streamlit run run_agent_app.py).
  • Extensibility: New sub-agents can be added by creating new directories under agents/ and updating agent_registry.json.

Highlighted Details

  • Automates buyer targeting and outreach across platforms like Instagram and TikTok.
  • Facilitates cross-platform promotions, content transformation, and posting with attachments.
  • Enables automated messaging and customer support with language detection.
  • Supports creator discovery and competitor monitoring by identifying influencers.
  • Inspired by Google's A2A and Anthropic's MCP, aiming to be an open agent protocol for LLM-enabled applications.

Maintenance & Community

  • Sponsored by TikHub, which provides APIs for social media data insights.
  • Support and contact available via email (lqiu314@gmail.com, evil0ctal1985@gmail.com) and GitHub handles (@callmeiks, @Evil0ctal).
  • A Discord server is available for community interaction.
  • TikHub provides extensive documentation and SDKs for their APIs.

Licensing & Compatibility

  • The README does not explicitly state the project's license.
  • Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

Requires obtaining and configuring API keys for each social media platform to be used, which can be a complex setup process. Deep integration with platforms implies potential reliance on their API stability and terms of service. The extensibility for adding new agents requires adherence to specific project structures and registry updates.

Health Check
Last Commit

9 months ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
170 stars in the last 30 days

Explore Similar Projects

Starred by Andrew Ng Andrew Ng(Founder of DeepLearning.AI; Cofounder of Coursera; Professor at Stanford), Jack Lukic Jack Lukic(Author of Semantic UI), and
5 more.

ag2 by ag2ai

0.3%
4k
AgentOS for building AI agents and facilitating multi-agent cooperation
Created 1 year ago
Updated 1 day ago
Feedback? Help us improve.