Sold by: Software Sushi
Deployed on AWS
Free Trial
Goose is an open source AI agent for the command line. Give it a task in plain English and it plans the steps, then reads and writes files and runs shell commands until the job is done, using the LLM provider you configure. This Ubuntu 24.04 image gives you a private agent workstation reachable through Session Manager, with no inbound ports.
Overview
Goose is an AI agent that works from your terminal. Instead of only suggesting code, it acts: you describe a task such as 'add input validation to this service and run the tests', and Goose uses its built-in developer tools to explore the project, edit files and run commands, checking results as it goes until the task is complete.
Agents that can run commands are best kept away from your personal workstation. This image gives developers a dedicated instance in their own account where Goose can work freely on the repositories you bring, with nothing exposed to the network.
What is included: the Goose command-line agent at /usr/local/bin/goose with its built-in developer extension, ready for the LLM provider sessions you configure, plus a guide at /opt/sushi/docs/README.md. Goose opens no inbound listener, no messaging gateway is enabled and no provider credentials are included.
Getting started takes a few minutes: launch t3.medium (2 vCPU, 4 GiB RAM) with a 16 GiB or larger encrypted gp3 root volume and IMDSv2, attach an instance profile with AmazonSSMManagedInstanceCore, allow outbound HTTPS and keep inbound rules closed. Connect with Session Manager and run sudo -iu ubuntu bash /opt/sushi/docs/demo.sh; Goose completes a real file-writing task against a local test model, so no paid model calls are made. Then configure your own provider credentials privately and run your first task, for example goose run --text "" --with-builtin developer. The linked Goose quickstart covers provider setup.
Pricing: a software fee of USD 0.02 per running t3.medium instance-hour. An optional five-day free trial for one concurrent instance changes software billing only and then converts to the hourly fee; the same full software is installed before and after it. This is not a separate trial or evaluation edition, and there is no product-imposed time, user or usage limit. Additional concurrent instances incur software fees. EC2, EBS, data transfer and any model-provider charges are billed separately, including during the free trial.
This is a repackaged open source software product wherein additional charges apply for independent AWS packaging, validation, maintenance and setup documentation. Goose is published by AAIF / Block under the Apache-2.0 license; Software Sushi provides the image, setup guide and packaging support and does not claim upstream endorsement. Workspace and session data stay on the root volume; back them up before replacing an instance, because a new image version does not migrate sessions or credentials.
Highlights
- Hand an AI agent a task in plain English. Goose plans the steps, edits files and runs commands with its built-in developer tools.
- Verified in minutes: the built-in check has Goose finish a real file-writing task against a local test model, with no paid model calls.
- Private agent workstation with no inbound ports and no baked credentials. You choose and configure the LLM provider.
Details
Sold by
Categories
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 24.04
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 5 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 | Cost/hour |
|---|---|
t3.medium Recommended | $0.02 |
Dimensions summary
You pay a single hourly software fee for each running instance, billed on the recommended t3.medium size (2 vCPU, 4 GiB RAM). This is a usage-based model with no upfront commitment, so charges accrue only while the instance runs. An optional five-day free trial covers the software fee for one instance, then converts to the same hourly billing. The software itself stays identical before and after the trial. EC2, EBS, data transfer, and your chosen model provider's charges are billed separately, including during the trial.
Top-of-mind questions for buyers
The fee covers the packaged command-line agent on Ubuntu 24.04, with its built-in developer tool for reading files, writing files, and running shell commands. It runs on a t3.medium instance (2 vCPU, 4 GiB RAM). You bring your own model provider; no model, credits, or keys are included.
The hourly software fee applies for each running instance. Charges stop when you stop the instance, since billing meters running time, not task activity. A stopped instance may still incur separate AWS storage fees for its encrypted root volume.
EC2 compute, EBS storage (at least a 16 GiB encrypted gp3 root volume), and data transfer are billed separately through AWS. Your chosen model provider also charges for its own usage. These separate charges apply even during the free trial.
docs.softwaresushi.com
Helpful?
Vendor refund policy
We offer a full refund of software charges for the first 48 hours billing starts if the product does not perform as described. To request a refund, email info@softwaresushi.com with your EC2 instance ID and a description of the issue. AWS infrastructure costs (EC2, EBS, data transfer) are billed by AWS and are not eligible for refund by us.
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
Goose v1.54.0 CLI agent (official upstream release, packaged by Software Sushi) on Ubuntu 24.04 LTS for t3.medium. Includes the built-in developer tools, customer-configured LLM providers, Session Manager access with no inbound ports, and an offline walkthrough at /opt/sushi/docs/demo.sh that uses a localhost model stub. No provider credentials are included.
Additional details
Usage instructions
- Launch t3.medium (2 vCPU, 4 GiB RAM) with a 16 GiB or larger encrypted gp3 root volume and IMDSv2. Attach an instance profile with AmazonSSMManagedInstanceCore, allow outbound HTTPS and keep inbound rules closed.
- Connect with aws ssm start-session --target <instance-id>. After cloud-init finishes, run: sudo -iu ubuntu bash /opt/sushi/docs/demo.sh (expect SUSHI_CUSTOMER_DEMO_PASSED).
- Read /opt/sushi/docs/README.md, then configure your LLM provider privately as ubuntu (keep keys out of user-data and logs).
- Run a task, for example: goose run --text "<your task>" --with-builtin developer Back up your workspace before replacing the instance. Documentation: https://goose-docs.ai/docs/quickstart Support: info@softwaresushi.com
Resources
Support
Vendor support
Software Sushi provides installation and configuration guidance for this image. Contact info@softwaresushi.com with your product version and the steps you took; never send credentials or private code. Guaranteed response times require a separate agreement. This offer does not include AAIF / Block 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.
Similar products
Agent Zero Core with a local workbench, cloud-model terminal/files and private Telegram. Customer cloud-model credentials are required after launch.
Nanobot with localhost WebUI, native Python tools and a private Telegram channel. Customer cloud-model credentials are required after launch.
Paid production AMI from Software Sushi that packages NVIDIA OpenShell v0.1.2 on Ubuntu 24.04 ARM64 with hardening, first-boot identity, a local mTLS gateway and support contact.
Production-ready Hermes AI messaging agent on hardened Ubuntu 24.04. Add your model-provider and Telegram credentials and run it in your AWS account.
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.