The startup offers a performance testing and application optimization platform that utilizes deep reinforcement learning and augmented intelligence to enhance data center energy efficiency. By leveraging advanced data science techniques, the platform helps businesses maintain operational uptime while reducing energy consumption.
Funding
$69M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
Managing Kubernetes resources efficiently is challenging due to the dynamic nature of workloads and the complexity of rightsizing, leading to over-provisioning, wasted resources, and increased cloud costs. Manual resource management is time-consuming and error-prone, while ensuring application reliability during rightsizing adds further complexity.
Solution
StormForge provides an automated Kubernetes resource management platform that leverages machine learning to continuously optimize workload resource allocation. The platform analyzes resource usage and horizontal pod autoscaler behavior to dynamically adjust CPU and memory requests and limits, ensuring efficient utilization and accurate forecasting of needs. By automatically rightsizing resources, StormForge reduces cloud costs, prevents performance issues like CPU throttling and OOM kills, and frees developers from infrastructure sizing tasks. The platform integrates with existing Kubernetes tools like HPA, KEDA, and Karpenter, and offers customizable configurations to balance savings and reliability.
Target Audience
The primary audience includes platform engineering teams and DevOps engineers responsible for managing Kubernetes infrastructure, optimizing cloud costs, and ensuring application performance and reliability.
Features
- Machine-learning-based recommendations for optimal CPU and memory settings
- Automated rightsizing of Kubernetes resources, continuously adjusting configurations based on workload patterns
- Forecast-based algorithms that analyze seasonal trends to predict resource needs
- Integration with Horizontal Pod Autoscaler (HPA) for bi-dimensional scaling
- Compatibility with Kubernetes tooling, including HPA, KEDA, and Karpenter
- Customizable optimization goals for reliability or savings
- Support for various limit configurations to meet unique organizational requirements
- Integration with cloud cost management tools for granular insights into Kubernetes costs
- Automatic discovery of new pods and capture of metrics for continuous optimization