Enterprise Deployment
Deploying Devin
Overview
Devin is designed for seamless integration into enterprise environments, with deployment options that balance speed, security, and compliance. Devin can be initiated through the web interface, Slack, or API, ensuring flexibility in how teams engage with the system.
Upon activation, Devin operates within a dedicated workspace that includes:
- A shell for executing commands.
- A browser for web-based interactions.
- A code editor for reading and writing code.
Devin’s workspace operates under the control of its brain, which always resides within Cognition’s Cloud.
Deployment Options
Devin supports two primary deployment models:
| Deployment Model | Primary Advantage | Considerations |
|---|---|---|
| SaaS | Fastest setup, managed infrastructure | Managed environment |
| VPC | Full data isolation, greater control | Requires additional setup time |
Choosing a Deployment Model
- SaaS Deployment: Recommended for organizations looking for a quick setup with minimal operational overhead. Deployment can be completed within minutes.
- VPC Deployment: Ideal for enterprises with strict security, compliance, or data isolation requirements. While deployment takes longer, it ensures full network and infrastructure control. This deployment architecture ensures zero data retention by storing all your data within your environment.
Once a deployment model is chosen, the next critical step is integrating source code repositories.
Devin’s Architecture
Virtual Private Cloud (VPC) Deployment
Devin VPC Architecture
SaaS Deployment
Devin SaaS Architecture
VPC Deployment Specifications
Deploying Devin in a Virtual Private Cloud (VPC) requires a dedicated server that meets the following requirements:
-
Hardware Requirements:
- Must support virtualization (Devin does not run in containers).
- Sufficient compute and memory resources based on usage.
-
Software Requirements:
- Cognition Agent Service installed on the provisioned server.
- Secure network connectivity to Cognition’s Cloud.
Cross-Tenant Communication
Devin’s architecture ensures secure communication between your VPC environment and Cognition’s Cloud.
Cognition's Tenant is Hosted on Azure
| Feature | Requirement |
|---|---|
| Networking | Egress access required |
| Ports | HTTPS/443 |
| Connection | On startup, Devin establishes a secure WebSocket connection to an isolated container in Cognition’s tenant |
| Communication | All subsequent operations occur over this secure channel |
| Isolation | Backend session isolation for enhanced security |
Granting internet access to Devin’s workspace is strongly recommended to ensure full functionality.
Deployment Guides
Use the following platform-specific guides to deploy Devin in your VPC environment:
AWS Deployment
Step-by-step guide for deploying Devin in AWS.
Azure Deployment
Instructions for setting up Devin in Azure.
SSO via Okta
Configure authentication using SAML & OpenID 2.0 with Okta.
SSO via Azure
Enable seamless authentication with Azure AD.
FAQs & Additional Information
Can we use our own LLM API keys?
Can we use our own LLM API keys?
Devin is a compound AI system and does not currently support third-party LLM API keys.
Do you support GCP?
Do you support GCP?
Please contact our sales team for information on Google Cloud Platform support.
Do you support OpenShift?
Do you support OpenShift?
OpenShift support is available upon request. Please reach out to our sales team for details.
Next Steps
- For SaaS Deployment: Start using Devin immediately by logging in to the web app.
- For VPC Deployment: Follow the AWS or Azure guides to configure your environment.
- Need Assistance? Contact our Enterprise Sales Team.