Sold by: SERAPH
Deployed on AWS
Open WebUI with Claude Code, Codex CLI and pi wired in as selectable chat models. Paste your provider keys on the built-in setup page and start working with real coding agents on an instance you own.
Overview
seraph hands you an AI agent workstation that is ready the moment your instance boots. Open a browser, paste your API key, and you are working with a real coding agent that reads your files, runs your commands and writes your code.
Three agents, one place. Claude Code, Codex CLI and pi are already set up and waiting. Pick the one you want and start working. There is no framework to assemble, no wiring to figure out and no terminal gymnastics required.
Your work stays on your infrastructure. The agents run inside your own AWS account, against your own files, using your own credentials. Nothing is routed through ours, and nothing leaves your account unless you send it there.
Your keys stay yours. Paste a key once and it lives only on your instance. There is no account to create with us, no subscription to manage, and no third party sitting in the middle of your work.
You decide how much freedom your agent has. Keep it answering questions, or hand it the keys and let it work directly on your project. One setting, your call, changeable at any time.
Ready in minutes. Launch it, paste a key, start chatting. Whether you are migrating a codebase, drafting documentation or exploring what an agent can do with your project, seraph stays out of the way and lets you work.
Highlights
- Chat with Claude Code, Codex CLI and pi from one browser interface
- Setup page writes each API key into that tool's own config, never into a browser
- Agents run on the instance and can read, run and edit code in place
Details
Sold by
Categories
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Rhel 9
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
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. Alternatively, you can pay upfront for a contract, which typically covers your anticipated usage for the contract duration. Any usage beyond contract will incur additional usage-based costs.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Cost/hour |
|---|---|
m4.large Recommended | $0.0411 |
i3en.large | $0.0685 |
m6idn.large | $0.0411 |
m5d.large | $0.0411 |
m6in.large | $0.0411 |
c8a.large | $0.0411 |
r5ad.large | $0.0685 |
m6id.large | $0.0411 |
m2.xlarge | $0.137 |
m8idb.large | $0.0411 |
Dimensions summary
You pay by the hour for the software running on your chosen EC2 instance type. Each dimension maps to one specific instance size, all at the .large size across many families. These families cover general purpose, compute, memory, storage, and graphics workloads. Pricing scales with the instance you select rather than with tiers or feature sets. You pick the instance that fits your performance and compliance needs, then run it inside your own AWS account. Billing tracks actual hours used, so cost reflects how long each instance runs.
Top-of-mind questions for buyers
You pay for the software running on your selected EC2 instance, billed per hour it runs. The listing provides ready-to-launch machine images with coding agents preinstalled and a shared chat interface. The software runs inside your own AWS account and network, so your code and keys stay in your infrastructure.
Software charges accrue only while the instance runs. A stopped instance does not accrue the hourly software fee. You may still owe underlying AWS fees, such as storage for the attached volume, but the software meters running time only.
Each dimension maps to one .large instance from a specific family. Families target different needs: general purpose, compute, memory, storage, and graphics workloads. You pick the family and select the region and network controls that fit your performance and compliance requirements, then run it in your account.
seraphimprod.com
Helpful?
Vendor refund policy
REFUND POLICY; seraph (AWS Marketplace AMI)
Request a full refund within 14 days of your first launch if seraph does not work as described. Covers the annual fee and hourly usage charges from that period.
Email support@seraphimprod.com with your AWS account ID, instance ID, and region. Refunds go to the original payment method via AWS Marketplace, typically within 5-10 business days.
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
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
An AI agent workstation built on Red Hat Enterprise Linux: Open WebUI with Claude Code, Codex CLI and pi available as chat models, and a setup page for your provider API keys
Additional details
Usage instructions
Launch the AMI with the instance type you need, then open the setup page at http://<instance-ip>:8090 and paste your provider API key. Open Open WebUI at http://<instance-ip>:8080 to create your administrator account and start working with the agents. Restrict ports 8080 and 8090 to your own network before exposing the instance publicly.
Resources
Vendor resources
Support
Vendor support
Email support is available at support@seraphimprod.com . Include your AWS account ID and the region of the affected instance.
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.
Similar products
Panther is a modern Security Information and Event Management (SIEM) tool that solves the challenges of security operations at scale.
Coveo unifies your enterprise content into a single permission-aware AI index, then delivers search, recommendations and grounded generative answers across commerce, service, website and workplace experiences, and to the agents you build on AWS.
Takara's DS1 Embedding Model is a high-speed, low-computing text embedding solution that now supports multiple languages, leveraging static embeddings for superior performance. Offering exceptional speed and near-OpenAI accuracy across global markets, it's ideal for applications demanding swift semantic responses, such as speech-to-speech, betting, and gaming. With an API compatible with OpenAI, DS1 ensures a seamless upgrade experience without language barriers.
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.