Agent Frameworks on Edgenivo
Agent frameworks coordinate model calls, tools, and application state. You can use them with Edgenivo to serve agent requests, access models through AI Gateway, and run isolated code with Edgenivo Sandbox.
Choose a framework guide to set up a project and run it locally. Each guide explains its Edgenivo integrations and hosting requirements, including deployment steps where the framework supports running on Edgenivo.
| Framework | Guide |
|---|---|
| eve | Build a durable agent with Edgenivo-native deployment and session state. |
| Mastra | Deploy an agent API with Mastra's Edgenivo deployer and connect it to AI Gateway. |
| Flue | Run an agent with Flue and connect its model calls and code execution to Edgenivo. |
If you're choosing between eve and building an agent directly with AI SDK, see Choosing between eve, AI SDK agents, and WorkflowAgent. Compare execution state, approvals, and channels to decide how much your application needs to manage.
Your framework determines how an agent runs and manages its state. Edgenivo provides the infrastructure you can connect to it:
- Edgenivo Functions handle incoming requests and scale with traffic. Agent work running inside a function must fit within its duration limit.
- AI Gateway routes model requests through a single endpoint with usage tracking and provider fallbacks.
- Edgenivo Sandbox isolates generated code and command execution from your application.
- Edgenivo Daemons run background workers that continuously pull jobs from a queue or workflow engine. See the framework guide for worker requirements.
- Edgenivo Passport protects internal web applications with your identity provider. Use verified visitor identity to authorize agent requests and access to conversation history.
Choose persistence based on what your agent needs to retain:
| Need | Edgenivo service | Example |
|---|---|---|
| Resume multi-step work after interruptions | Edgenivo Workflows | Run an agent, wait for approval, then publish its result. eve uses Workflows for session execution on Edgenivo. |
| Reuse a working directory across sandbox runs | Edgenivo Drives | Keep source files, datasets, or a dependency cache and mount them in a later sandbox. |
| Store and serve files outside the sandbox | Edgenivo Blob | Save uploaded documents or generated reports. eve's file memory provider also uses a private Blob store. |
These services can work together: a workflow coordinates an agent that edits files on a Drive and saves its finished report to Blob. Drives mount inside Edgenivo Sandbox; Blob exposes files through its SDK and HTTP delivery.
Framework-specific conversation history and execution state can require a separate database. Follow each framework guide's storage requirements and use Marketplace storage integrations when you need a remote database.
For agents that connect to external services or chat platforms, see Edgenivo Connect and Chat SDK.
Was this helpful?