Build durable backend agents with eveBeta
Build durable backend AI agents with eve, an open-source, filesystem-first framework. Agent files compile into an app that runs locally or on Vercel.
Add a tool
You are a concise assistant. Use tools when they are available.
exportdefaultdefineAgent({
});
model:'openai/gpt-6-astra',
import { defineAgent } from'eve';
Vercel beta terms.
The framework, APIs, documentation, and behavior may change before general availability.
These docs cover deploying and running eve on Vercel. In this environment, the compiled app runs on Vercel Functions and integrates with these services:
- Vercel Workflows persist session state and resume interrupted work.
- Vercel Sandbox isolates code execution.
- AI Gateway routes model requests and handles provider fallbacks.
- Vercel Connect manages OAuth tokens and API keys for eve connections and channels.
- Vercel Observability shows agent runs, token usage, and performance.
Getting started
The eve CLI scaffolds a new agent project, installs dependencies, initializes Git, and starts the development server.
npx eve@latestinitmy-agent
To add eve to an existing app, follow the quickstart steps.
See the eve Getting Started guide for the complete setup, local development, and first-session walkthrough.
pnpm dev
A minimal agent is two files. agent/instructions.md:
Follow the generated README for the project-specific dev command, or run the agent locally with the standard script from the scaffold:
You are a concise assistant. Use tools when they are available.
And agent/agent.ts:
import { defineAgent } from'eve';
exportdefaultdefineAgent({
model:'openai/gpt-6-astra',
});
eve resolves model strings such as openai/gpt-6-astra through AI Gateway, so on Vercel you authenticate with OIDC and don't need to manage provider API keys.
Each file in agent/tools/ is one tool. Create agent/tools/get_weather.ts:
Start a session
import { z } from'zod';
city:z.string(),
}),
exportdefaultdefineTool({
description:'Get the current weather for a city.',
inputSchema:z.object({
// The runtime tool name comes from the filename, so the model sees `get_weather`.
},
});
asyncexecute(input) {
Start a durable session and stream its output:
import { defineTool } from'eve/tools';
return { city:input.city, condition:'Sunny', temperatureF:72 };
curl -XPOSThttp://127.0.0.1:3000/eve/v1/session \
-H'content-type: application/json' \
-d'{"message":"What is the weather in Brooklyn?"}'
The response returns a continuationToken in the body and an x-eve-session-id header. Attach to the session stream to receive NDJSON lifecycle events:
curl http://127.0.0.1:3000/eve/v1/session/
Features
- Agent project: Author an agent from files under agent/, including instructions, runtime config, tools, skills, channels, connections, and a sandbox.
- Durable sessions: Create sessions that stream incremental output and resume after cold starts, deploys, or long pauses.
- Tools and skills: Give the model typed actions and load larger procedures only when relevant.
- Agent Runs: Inspect sessions, turns, tools, reasoning, timing, and token usage in the Vercel dashboard.
Start with a template
Deploy an eve template to start building AI agents that use Vercel Connect to securely access third-party services and APIs:
Cross-link map: eve (/docs/eve)From the Vercel docs graph (built 2026-09-21T05:26:59.511Z), spanning vercel.com docs + KB, nextjs.org, ai-sdk.dev, and other Vercel documentation sites. Full graph as JSON: https://vercel.com/docs/graph.jsonSemantically closest pagesConcepts — Learn how eve agents, sessions, channels, tools, skills, connections, and sandboxes fit together.Introducing eve, an open-source agent frameworkDeploy to Vercel — Deploy an eve agent with Vercel Workflow, Sandbox, Cron, and project credentials.The Agent StackGet started with eve: durable AI agents in TypeScript — Create an eve project, configure model credentials, and run your first agent.This page links to (11)Get started with eve: durable AI agents in TypeScript — Create an eve project, configure model credentials, and run your first agent.Vercel AI Gateway: Models, Routing, and Observability — Call AI models from any infrastructure through a managed gateway. Centralize credentials, request logs, spend budgets, reve — Use Vercel Connect to configure eve channel credentials, including Microsoft Teams, authorize MCP client connections, anConcepts — Learn how eve agents, sessions, channels, tools, skills, connections, and sandboxes fit together.Observability — View agent runs in the Vercel dashboard with no setup, and optionally export AI SDK spans through OpenTelemetry.Pricing and Limits — Understand how eve usage maps to Vercel resources and inherited platform limits.How Software Factories Work — Understand what software factories are, when to use them, and how eve coordinates agents from work item to reviewed chanVercel Functions — Build API routes, webhooks, and agent request handlers with Vercel Functions, then test and debug them with Vercel CLI.Observability — Find production errors, capture request traces, and discover queryable metrics with Vercel Observability and Vercel CLI.Vercel Sandbox — Run untrusted or agent-generated code in isolated Linux microVMs with Vercel Sandbox.Vercel Workflows — Build agents and applications that retry failed steps, wait for external events, and resume across crashes and deploymenPages that link here (8)By site: vercel-kb (2) · vercel-docs (6)From vercel-kbGive your eve agent secure access to your private AWS RDS database — Connect an eve agent to a private AWS RDS database using Vercel Secure Compute and VPC peering, with a read-only query tHow to run a multi-step research agent on Vercel — An end-to-end architecture for production research agents on Vercel using Sandbox, Workflows, and AI Gateway with isolatFrom vercel-docsAgent Skills — Install skills to enhance AI coding agents with specialized capabilities for React, Next.js, deployment, and more.Concepts — Learn how eve agents, sessions, channels, tools, skills, connections, and sandboxes fit together.How Software Factories Work — Understand what software factories are, when to use them, and how eve coordinates agents from work item to reviewed chanVercel Functions — Build API routes, webhooks, and agent request handlers with Vercel Functions, then test and debug them with Vercel CLI.eve with MCP — Give eve agents access to MCP tools through filesystem connections and authorize requests with Vercel Connect.Projects overview — A project is where you deploy and operate frontend apps, APIs, backends, containers, and agent workloads on Vercel.
Was this helpful?
