Sold by: Cloudology
Deployed on AWS
Free Trial
Agentic AI for Kubernetes operations. Clu runs inside your cluster, uses your own Amazon Bedrock for inference, and makes troubleshooting, cost analysis, and safe write operations a chat-first workflow. Every write requires explicit operator approval - cluster data never leaves your AWS account.
Overview
Clu is an agentic AI-powered operations platform for Kubernetes, built for platform engineers and SREs who run production clusters. Unlike SaaS observability tools, Clu runs entirely inside your cluster - telemetry, chat context, and generated artifacts never leave your AWS account. Inference runs on your own Amazon Bedrock, so your data and your model stay under your IAM boundary.
Three modules stack to fit your team's scope. Cluster Agent (always on) handles Kubernetes troubleshooting, automatic knowledge-graph scanning, scheduled health reports, convention detection, and Prometheus + CloudWatch integration. Cloud Agent adds IAM and IRSA mapping, managed-service discovery (RDS, ElastiCache, S3, ECR), VPC topology, cost analysis, and Terraform generation for AWS resources. IDP Platform adds application scaffolding, manifest generation, Helm golden paths, and safe write operations - every change dry-runs first and requires explicit operator approval before it lands.
Safety is a first-class invariant: protected namespaces (kube-system, kube-public, and any flagged by policy) are hardcoded and cannot be overridden by configuration. Writes go through a two-step gate - the agent produces a dry-run and diff, parks the request in an approval queue visible in the in-cluster UI, and only executes after an operator explicitly clicks Approve. Every approved action is logged with the operator's identity for audit review.
Deployed as a single pod with a browser UI reachable via kubectl port-forward or your own ingress, Clu runs on both AMD64 and Graviton (ARM64) from day one, connects to Bedrock via IRSA or EKS Pod Identity, and requires no outbound network beyond Bedrock itself - air-gap friendly for regulated environments.
Highlights
- Your cluster telemetry and chat context never leave your AWS account. Inference runs on your own Amazon Bedrock, scoped by IAM. No SaaS control plane, no third-party data collection, no outbound dependency beyond Bedrock itself. Air-gap friendly for regulated and FedRAMP environments.
- Every write produces a dry-run and diff, lands in an approval queue, and only executes after an explicit operator click. Protected namespaces are hardcoded - no config can override them. Every approved action is logged with operator identity, so you always know who applied what and when.
- Start with Cluster Agent for Kubernetes troubleshooting on any conformant cluster. Add Cloud Agent for AWS inventory, IRSA mapping, and cost analysis. Add IDP Platform for scaffolding, golden paths, and gated write operations. Each module is independently licensable - pay for what you actually use.
Details
Sold by
Delivery method
Supported services
Delivery option
ECR Delivery
Helm Install
Latest version
Operating system
Linux
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 30 days according to the free trial terms set by the vendor. Usage-based pricing is in effect for usage beyond the free trial terms. Your free trial gets automatically converted to a paid subscription when the trial ends, but may be canceled any time before that.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/unit/hour |
|---|---|---|
Hours | Container Hours | $0.10 |
Dimensions summary
You pay one usage-based rate for each container hour that Clu runs. AWS meters your pod uptime automatically and bills per hour. This single flat rate covers every module in the subscription. Modules act as capability gates, not separate price points. There is no metering per API call, per tool, or per module. Your cost scales only with how long the container runs. For example, running continuously for a month bills the hourly rate across those hours.
Top-of-mind questions for buyers
AWS meters the uptime of the Clu pod running in your EKS cluster. Each hour the pod runs counts as one container hour. Billing tracks running time only, so a pod running around the clock for a month bills the hourly rate across those hours.
Charges apply only while the pod is running and metering uptime. If you scale the pod down or stop it, container hours stop accruing. The flat rate covers every module during runtime, so pausing the workload directly reduces your metered hours.
No. Inference runs through your own AWS account and bills to that account at standard AWS rates. Cloudology does not proxy or mark up this usage. Your Clu charge covers container hours only, with no per-API, per-tool, or per-module metering added.
getclu.dev
Helpful?
Vendor refund policy
Clu offers a 30-day free trial to evaluate functionality prior to paid usage. Refunds for paid hourly charges are considered case-by-case for: (1) sustained product defects preventing core functionality, or (2) documented service unavailability exceeding 24 hours in a billing period. Refund requests must be submitted within 30 days of the charge. Contact: support@cloudology.cloud
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
ECR Delivery
Supported services: Learn more
- Amazon EKS
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Clu v0.2.5. See https://getclu.dev/ for documentation.
Additional details
Usage instructions
Pull the backend and frontend images from your subscribed ECR. Both images are multi-arch (linux/amd64 + linux/arm64).
You will also need to set up:
- IAM role for ServiceAccount (IRSA) granting bedrock:InvokeModel and the per-module read permissions
- The 'clu-ops' namespace and ServiceAccount 'clu-ops-agent'
- ClusterRole 'clu-ops-reader' (always) and 'clu-ops-writer' (Module 3 only)
- ConfigMap with BEDROCK_REGION, MARKETPLACE_PRODUCT_CODE, module toggles
- Service exposing the frontend on port 8080
Full manifests + IAM policies + step-by-step setup: https://getclu.dev/docs/install
For most installs, the Helm or EKS Add-on delivery options handle this wiring automatically.
Resources
Vendor resources
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.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.