Sold by: Software Sushi
Deployed on AWS
Run the open-source Browser Use Python agent with local headless Chromium and your own model provider on Ubuntu 24.04. This product has charges associated with it for seller support and packaging.
Overview
This product has charges associated with it for seller support and packaging. Software Sushi packages the unmodified historical Browser Use 0.10.1 open-source release, local headless Chromium, an account-authenticated command-line launcher and an independently checked records-and-form walkthrough for Ubuntu 24.04 x86_64.
Getting started: use t3.medium or larger with at least 4 GiB RAM and 24 GiB storage. Connect through AWS Systems Manager Session Manager or your SSH access setup and run sudo -iu ubuntu bash /opt/sushi/docs/demo.sh. The included walkthrough uses a deterministic local model fixture and a local synthetic page, so it needs no provider account. For model-driven tasks, configure your own OpenAI-compatible chat-completions provider with JSON schema structured output using sushi-browser-use configure. Provider compatibility depends on the selected model. The customer guide is installed at /opt/sushi/docs/README.md.
What is and is not included: the product provides a local Python library and command-line workflow, with no web dashboard or public task API. Model credits, Browser Use Cloud services, hosted browsers and proxy subscriptions are not included. Chromium runs as ubuntu with its sandbox enabled. Domain navigation controls are not a network isolation guarantee. Task histories, browser profiles and provider settings persist on the instance root volume.
Licensing: Browser Use is an independent open-source project and is not affiliated with Software Sushi. The Browser Use name and logo belong to the Browser Use project and are used only to identify the software; the upstream project does not endorse this packaging. Original open-source licenses govern the application and dependencies; packaging/support charges do not replace them. Complete original notices and matching retained source inputs are readable on the instance. The lxml corresponding libiconv, libxml2, libxslt and zlib archives accompany the original source and documented rebuild entrypoint.
Software is USD 0.03 per running instance-hour; EC2, EBS, transfer and provider charges are separate. English customer guide: https://softwaresushi-marketplace-branding-public.s3.us-east-1.amazonaws.com/docs/browser-use/ba7631ec0b86f6df76e6/getting-started.html
Highlights
- Local Browser Use Python agent and Chromium browser, with no hosted-browser subscription included.
- Bring your own compatible model provider; account-authenticated launcher and per-task output directories.
- Synthetic form walkthrough with actual browser submission, saved records and independent hash-checked readback.
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
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 | $0.03 |
t3.large | $0.03 |
t3.xlarge | $0.03 |
t3.2xlarge | $0.03 |
Dimensions summary
You pay by the hour for the EC2 instance size you run this browser agent on. The four dimensions map to four instance types: t3.medium, t3.large, t3.xlarge, and t3.2xlarge. These are not feature tiers. They differ by compute and memory capacity, so pricing scales with the instance size you select. You pick one size at launch based on your workload needs. The software runs in your own AWS account. AWS infrastructure, data transfer, and third-party model-provider charges are billed separately from this hourly software rate.
Top-of-mind questions for buyers
Each size maps to an EC2 instance with set compute and memory. The t3.medium has the least capacity; the t3.2xlarge has the most. You pick a size at launch based on how many browser sessions and how much memory your workload needs. You can relaunch on a different size later.
The hourly software charge applies while the instance runs. A fully stopped instance does not accrue the hourly software rate. Stopped instances may still incur AWS storage fees for attached volumes, which are billed separately from this software charge.
AWS infrastructure such as EC2 compute, storage, networking, and data transfer is billed separately. You also provide your own model-provider keys after launch. Those third-party model providers and any messaging platforms may charge for their own usage. Review each AWS Marketplace listing for current terms.
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 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
Browser Use 0.10.1 on Ubuntu 24.04 x86_64 with local headless Chromium, an account-authenticated launcher, native DOM records calculation and real browser form submission. Original wheel notices, matching retained sources and the lxml linked-library corresponding sources/rebuild instructions are included. Configure your own compatible model provider after launch. No model weights, credits, hosted browsers or Browser Use Cloud service are included. Recommended t3.medium, at least 4 GiB RAM and 24 GiB root storage.
Additional details
Usage instructions
Launch t3.medium or larger x86_64 with at least 4 GiB RAM and 24 GiB encrypted gp3 root storage, and require IMDSv2. Software is USD 0.03 per running instance-hour; EC2, EBS, data transfer and model-provider usage are separate. Use AWS Systems Manager Session Manager with your own appropriate instance profile and outbound endpoint access; sessions initially open as ssm-user. SSH is an alternative with your own key and restricted administrative CIDR. No public application port is needed. Wait for automatic cloud initialization, then run sudo -iu ubuntu bash /opt/sushi/docs/demo.sh. This local walkthrough uses a deterministic model fixture, the real Browser Use agent and Chromium, a synthetic local page and an actual local form POST. It independently rereads three records totaling 42 and prints SUSHI_CUSTOMER_DEMO_PASSED. For model-driven tasks, switch to ubuntu, run sushi-browser-use configure in an unrecorded terminal, and enter your exact compatible OpenAI-style HTTPS chat-completions endpoint, model and hidden key. JSON schema structured output is required; compatibility depends on the model/provider. Then run sushi-browser-use demo with a new output directory beneath $HOME/browser-use-results. The model selects a native DOM read/calculation tool before submitting the local form. Model credits, subscriptions, hosted browsers and weights are not supplied. Keep keys out of task files, commands, histories and recordings. Settings are mode0600 at /home/ubuntu/.config/sushi/browser-use/provider.json; results and browser profiles persist on root EBS and are not automatically backed up. Inspect saved tasks with python3 -I -B /opt/browser-use/readback.py /absolute/path/to/completed/run. Protect raw histories/profiles as account data. Chromium sandbox remains enabled; domain controls are not a network firewall. For recovery, inspect sushi-browser-use-firstboot.service and its journal without disabling AppArmor or the browser sandbox. Preserve failed tasks and use new output directories. Original notices are under /usr/share/doc/browser-use, original wheels/sources under /opt/browser-use, and the detailed guide is /opt/sushi/docs/README.md. English guide: https://softwaresushi-marketplace-branding-public.s3.us-east-1.amazonaws.com/docs/browser-use/ba7631ec0b86f6df76e6/getting-started.html
Resources
Vendor resources
Support
Vendor support
Software Sushi provides AMI packaging and setup guidance. Contact info@softwaresushi.com for installation questions. Support coverage requires a separate agreement; upstream project and model-provider support are not included.
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
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.
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.
Anchor Browser is agentic infrastructure for web automation, enabling AI agents to complete any web-based process by clicking, typing, navigating, and reasoning like a human in real time. It removes integration barriers across disconnected apps, making even complex manual workflows fully automatable.
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.