Overview
Refly on CentOS 9 is a cutting-edge Amazon Machine Image (AMI) designed to redefine how teams interact with Artificial Intelligence. As the first open-source agentic workspace, Refly goes beyond simple chat interfaces by providing a free-form canvas where human insight and AI execution blend seamlessly. It allows users to build, govern, and deploy deterministic "Agent Skills" rather than just fragile prompts.
Maintained and optimized by ThinkCloud, this AMI is deployed on a hardened CentOS 9 foundation. We have pre-configured the environment to handle complex multimodal workflows including text, image, audio, and video generation ensuring high-performance execution of AI-driven SOPs (Standard Operating Procedures). By self-hosting Refly, you maintain total data sovereignty and break free from the "black box" of third-party AI SaaS platforms.
Refly serves as a universal bridge between your enterprise toolchain (Slack, Feishu, GitHub, etc.) and the next generation of AI models. With ThinkCloud's enterprise support, you can transform your business logic into production-ready agentic infrastructure that is secure, version-controlled, and highly scalable.
Highlights
- Revolutionary Human-AI Collaboration Move beyond basic prompting with an agentic workspace that compiles your enterprise SOPs into executable skills, ensuring 100% operational compliance and reliability.
- Privacy-First AI Infrastructure Take full control of your AI strategy. Host your models, skills, and data on a secured CentOS 9 instance within your own VPC, protected by ThinkCloud's expert configuration.
- Enterprise Support by ThinkCloud Leverage professional guidance for scaling AI workloads, managing model providers, and integrating Refly into your existing DevOps pipelines for maximum efficiency.
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimension | Cost/hour |
|---|---|
t3.large Recommended | $0.10 |
t3.micro | $0.10 |
t3a.large | $0.10 |
t3.medium | $0.10 |
t3a.medium | $0.10 |
t3a.nano | $0.10 |
t3.nano | $0.10 |
t3a.micro | $0.10 |
t3.small | $0.10 |
t3a.small | $0.10 |
Vendor refund policy
no refunds
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Updated to the latest
Additional details
Usage instructions
SSH to the instance and login as 'ec2-user' using the key specified at launch. Additional information may be found at : https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/AccessingInstancesLinux.html After entering the system, please check the Readme file under the /root path, which contains detailed configuration information
Support
Vendor support
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.