AI/ML

    Deploy OpenManus on AWS EC2 : Easy Setup and Configuration


    Introduction

    OpenManus, an open-source replication of the ManusAI agent system, became available on GitHub in March 2025, gaining over 16,000 stars in days. Built by MetaGPT contributors, it offers a modular AI agent framework. This document details how to download and deploy OpenManus on Amazon Web Services (AWS) as of March 12, 2025, tailored for developers in India or globally seeking scalable cloud hosting.

    Prerequisites

    • Basic CLI Knowledge: Familiarity with Linux commands.
    • AWS Account: Sign up at aws.amazon.com with a free tier option.
    • Git Installed: Available locally (git-scm.com).
    • AWS CLI: Installed and configured (aws configure with access keys).

    Step-by-Step Deployment on Azure

    Step 1: Launch an EC2 Instance

    1. Log into AWS Console: Navigate to EC2 > Instances > Launch Instances.

    2. Configure Instance:

      • AMI: Ubuntu Server 22.04 LTS (free tier eligible).

      • Instance Type: t2.medium (4GB RAM, 2 vCPUs) for basic use; t3.large recommended.

      • Storage: 30GB EBS volume.

      • Security Group: Allow ports 22 (SSH), 5000 (API), 8000 (Web UI).

    3. Launch: Download the .pem key file for SSH access.

    Step 2: Connect to EC2

    SSH In:

    ssh -i <your-key.pem> ubuntu@<ec2-public-ip>

     

    Step 3: Install Dependencies

    Update System:

    sudo apt update && sudo apt install -y python3-pip python3-venv git

     

    Install UV (Recommended):

    curl -LsSf https://astral.sh/uv/install.sh | shsource $HOME/.cargo/env

     

    Step 4: Download OpenManus

    Clone Repository:

    git clone https://github.com/mannaandpoem/OpenManus.gitcd OpenManus

     

    Step 5: Configure and Install

    Set Up Config:

    Copy example config:

    cp config/config.example.toml config/config.toml

     

    Edit config.toml with your API key (e.g., OpenAI):

    [llm]model = "gpt-4o"base_url = "https://api.openai.com/v1"api_key = "your-api-key"

     

    Install Dependencies:

    uv pip install -r requirements.txt

     

    Step 6: Run OpenManus

    Launch:

    python3 main.pyAccess api at http://<ec2-public-ip>:5000, Web UI at http://<ec2-public-ip>:8000 (if enabled).

     

    Troubleshooting

    • Port Issues: Check security group rules in AWS Console.
    • Memory Errors: Upgrade to a larger instance (e.g., t3.large).

     

    Conclusion

    Deploying OpenManus on AWS is straightforward with an EC2 instance, leveraging GitHub’s open source availability. This setup offers scalability and accessibility for developers in India, utilizing AWS’s robust infrastructure. Start with a t2.medium instance and scale as needed your AI agent is now cloud ready.

    Ready to optimize your AI infrastructure? Contact us today and leverage our AI/ML expertise!  

    Share

    facebook
    LinkedIn
    Twitter
    Mail
    AI/ML

    Related Center Of Excellence