eve

Beta

eve is a filesystem-first framework for durable backend AI agents. You define each agent with files under an agent/ directory. eve discovers those files and compiles them into an app that runs on Vercel Functions.

eve uses these Vercel 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 external services.
• Vercel Observability shows agent runs, token usage, and performance.

The fastest path is the eve CLI. Run the published package with npx to scaffold a new agent project, install dependencies, initialize Git, and start the development server:

npx eve@latest init my-agent

To add eve to an existing app, follow the quickstart steps.

Follow the generated README for the project-specific dev command, or run the agent locally with the standard script from the scaffold:

pnpm dev

A minimal agent is two files. agent/instructions.md:

You are a concise assistant. Use tools when they are available.

And agent/agent.ts:

import { defineAgent } from 'eve';
 
export default defineAgent({
  model: 'openai/gpt-5.4-mini',
});

eve resolves model strings such as openai/gpt-5.4-mini 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:

import { defineTool } from 'eve/tools';
import { z } from 'zod';
 
// The runtime tool name comes from the filename, so the model sees `get_weather`.
export default defineTool({
  description: 'Get the current weather for a city.',
  inputSchema: z.object({
    city: z.string(),
  }),
  async execute(input) {
    return { city: input.city, condition: 'Sunny', temperatureF: 72 };
  },
});

Start a durable session and stream its output:

curl -X POST http://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/<sessionId>/stream

• 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.