Sold by: Grengin
Deployed on AWS
AWS Free Tier
Free, open-source, self-hosted AI workspace for your whole team: governed multi-LLM chat with OpenAI, Anthropic Claude, and open models. Bring your own API keys. Live in about 5 minutes.
Overview
Grengin gives your whole company a branded AI chat workspace with enterprise-grade governance, without enterprise pricing or vendor lock-in. Built for startups and small to mid-sized teams, it runs entirely in your own AWS account, and Grengin is never in the data path: traffic flows directly between your infrastructure and the model providers you choose. IT gets control, executives get insights, and every employee gets AI that is safe to use at work.
One governance layer covers every model your team uses. Connect OpenAI, Anthropic Claude, and 7+ open-source models, then manage them through a single admin dashboard with SSO, user management, and policies per department or project. Built-in PII detection and full audit trails keep sensitive data visible and reviewable, while real-time cost tracking and budget controls keep spend predictable. Grengin also connects to your existing stack through MCP, Jira, Confluence, and Google Drive.
The software is free and open source (github.com/grengin-oss/grengin). You pay only your standard EC2 infrastructure costs, and you bring your own API keys, so model usage is billed directly by your providers with no markup, no per-seat fees, and no minimums. Launch this AMI, connect your keys, and invite your team: most deployments are live in about 5 minutes with no DevOps expertise required.
Highlights
- One governance layer for every model: OpenAI, Anthropic Claude, and 7+ open-source LLMs behind a single admin dashboard with SSO, department-level policies, PII detection, and full audit trails.
- Free and open source: $0 software cost, pay only your EC2 infrastructure. Bring your own API keys, with no per-seat fees and no markup. Source at github.com/grengin-oss/grengin.
- Live in about 5 minutes with no DevOps required: launch the AMI, connect your keys, invite the team. Real-time cost tracking and budgets keep AI spend predictable per user, department, or project.
Details
Sold by
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 24.0.4
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
This product is available free of charge. Free 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.
Dimensions summary
You pay by the hour for the AWS EC2 instance you pick, not per user or per seat. Each dimension maps to a different EC2 instance type, so your rate scales with the compute size and family you choose. Smaller shared-core options like t3.small and t3a.small suit light use, while larger compute- or memory-focused types such as c8id.xlarge, m8i.large, and r8a.medium handle heavier workloads. The software itself carries no license fee. You also pay your AI model providers directly for usage. Choose the instance that matches your expected load and region.
Top-of-mind questions for buyers
Each dimension maps to one AWS EC2 instance type, such as c8id.xlarge or t3.small. You pay by the hour for the running instance you choose. The software adds no license fee or metering. Your bill scales with the instance family and size you select, not with the number of users.
You pay for running instance-hours only. A stopped or powered-off instance does not accrue hourly charges. Stopped instances may still incur AWS storage fees for attached volumes, but the hourly rate meters running time. Shut the instance down anytime to stop the hourly cost.
Two other costs apply. You pay each AI model provider directly for usage on your own API keys, with no markup added. You also pay standard AWS compute rates for the instance you run. The software itself carries no per-seat fee or separate license charge.
grengin.com
Helpful?
Vendor refund policy
Grengin is free software with a $0 software price on AWS Marketplace, so there are no software charges to refund. Standard AWS infrastructure charges (for example EC2 instances and EBS storage) are billed by AWS and are governed by AWS billing policies; direct questions about those charges to AWS Support. If you believe you were charged a software fee for this product in error, contact support@grengin.com and we will work with AWS to resolve it.
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
Initial AWS Marketplace release of Grengin (v0.3.1). This image provides a ready-to-run, self-hosted Grengin deployment that launches in about five minutes on your own AWS account. You bring your own model-provider API keys, and your data and traffic stay within your environment.
Included in this version:
- Grengin platform v0.3.0, pre-installed and configured on CentOS
- Multi-LLM access to OpenAI, Anthropic Claude, Google Gemini and open-source models through one unified governance layer
- Admin dashboard with user management, SSO, and department/project-level policies
- PII detection and full audit trails
- Real-time cost tracking and budget controls per user, department, and project Integrations: any MCP server, plus Jira, Confluence, and Google Drive
Getting started: After launch, open the instance to complete first-run setup, add your provider API keys, and invite your team. See [https://grengin.com/community ] for configuration and SSO setup. Bring-your-own API keys are required to connect model providers. Future versions will document changes in these notes.
Additional details
Usage instructions
Grengin Usage Instructions
1. Launch the instance
Use at least 2 GB RAM and a 10 GB disk: t3.small (x86_64) or larger. In the security group, allow inbound:
- TCP 80 (HTTP) required; serves the setup wizard and then the app.
- TCP 443 (HTTPS) required only if you enable SSL.
- TCP 22 (SSH) for administration (login user: ec2-user). Tip: restrict ports 80 and 22 to your admin IP during setup. The wizard is unauthenticated until you finish it.
2. Run the setup wizard
On first boot the instance auto-starts a one-time web installer. Wait about a minute, then browse to: http://<instance-public-ip>/ The wizard walks through:
- System check: verifies OS, free ports, RAM and disk.
- Database: install a local PostgreSQL (default) or connect to an existing one (host, port, user, password, database).
- Domain (optional): enter a domain and optionally enable HTTPS (free Let's Encrypt certificate; needs a contact email and the domain's DNS A record already pointing at this instance). On EC2 you can instead claim a free *.grengin.com subdomain offered in the wizard. Skip to run on the bare IP.
- Sign-in / SSO (optional): add Google and/or Microsoft Entra (Azure AD) OAuth credentials, set allowed email domains and just-in-time user provisioning. If you skip this, Grengin's hosted SSO proxy is enabled so you can still sign in.
- AI providers (optional): paste API keys for OpenAI, Anthropic, Mistral and/or Gemini, and tune RAG (retrieval) options. These can be added later.
- Install: click Install. The installer generates unique secrets, writes configuration, installs the API and web app, configures nginx, and creates and starts the application service. When it finishes, the wizard shows your access URL.
3. First use
- App URL: your domain (https if SSL enabled) or http://<instance-ip>/. The API is served under /api.
- There is no default password. The first account you register through the web UI becomes your initial user. JWT and encryption secrets are generated uniquely per instance. Nothing sensitive is baked into the image.
4. Administering the instance
SSH in as ec2-user, then use sudo.
- Service: sudo systemctl status grengin / sudo systemctl restart grengin
- App logs: sudo journalctl -u grengin -f
- Installer logs: sudo journalctl -u grengin-installer Key locations:
- Configuration / environment: /etc/grengin/.env
- API binary: /opt/grengin/grengin-api
- Web app files: /var/www/grengin
- Nginx site: /etc/nginx/conf.d/grengin.conf To change the domain, SSL, AI keys or other settings later, edit /etc/grengin/.env (or use the helper scripts in /opt/grengin/scripts) and run sudo systemctl restart grengin.
5. Security notes
- Finish the wizard promptly. Until you do, port 80 serves an unauthenticated installer. Keep the security group locked to your IP during setup.
- The image enforces IMDSv2 and disables root and password SSH login.
- Run behind HTTPS in production (enable SSL in step 3).
Resources
Vendor resources
Support
Vendor support
Grengin is free, open-source software maintained by a dedicated team, and every deployment includes support through the following channels. Email support@grengin.com for help with deployment, configuration, SSO, and connecting model provider API keys; we respond within one business day, Monday to Friday. Documentation, including the AWS quick start guide, is available at https://grengin.com/docs . Bug reports and feature requests are tracked publicly on GitHub at https://github.com/grengin-oss/grengin/issues and are triaged daily. To report a security vulnerability, email security@grengin.com and we will acknowledge within one business day. The software receives regular releases with security patches, published as new versions of this listing.
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
Grengin is a self-hosted, multi-LLM AI workspace: governed access to OpenAI, Anthropic Claude, and open-source models in one branded chat, live in about five minutes. Bring your own API keys, keep your data on your own infrastructure, and give IT the admin controls, SSO, PII detection, audit trails, and per-user cost limits without enterprise pricing or vendor lock-in.
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.