Skip to main content
VercelLaunch

Vercel releases eve: an open-source AI agent framework where each agent is a directory of files mapped to capabilities.

What happened

Vercel Inc. launched eve, an open-source framework for building, running, and scaling agents on Jun 17th '26.

Source

Article excerpt

Highlighted: the sentence this signal was extracted from

Vercel releases eve: an open-source AI agent framework where each agent is a directory of files mapped to capabilities. June 17, 2026 Vercel has released eve, an open-source framework for building, running, and scaling agents. The project is published as the npm package eve, licensed under Apache-2.0. Building an agent should mean defining what it does. It should not mean assembling all the plumbing that an agent needs to run in production. eve is the framework Vercel builds and runs its own agents on. According to Vercel post, it runs more than a hundred agents in production today. What is eve? eve is a filesystem-first framework for durable backend agents. You create an agent as a directory on disk. The directory is the contract. Each file describes one component of the agent. At a glance, the tree shows what an agent is and does. It also shows where it lives and when it acts on its own. The smallest agent that runs is two files. One sets the model. The other sets the instructions. // agent/agent.ts import {defineAgent} from "eve"; export default defineAgent({ model: "anthropic/claude-opus-4.8",}); The model is one line, and provider fallbacks are supported through AI Gateway. The instructions.md file becomes the system prompt that eve puts in front of every model call. An agent is a directory. Vercel's core idea is that agents have a shape. Every team kept...

Keep reading with a free account

The rest of this article, and every signal for Vercel, is in your free account.

Extracted by Autobound

From the Signal API record
Event
Launch

What this signalsA launch often needs new go-to-market and support spend.

Takes effect
Jun 17, 2026

The full record

From the Signal API record

Details

Product
eve, an open-source framework for building, running, and scaling agents

Extraction

Confidence
97%
Detected
Jun 17, 2026
signal_type
news
signal_subtype
launches

Use this data

Get every launch signal for Vercel and the companies you sell to, in the tools you already use.

  1. Ask Claude about it

    Connect Autobound to Claude, Claude Code or Cursor with MCP. Then ask: “What changed at Vercel this week?”

  2. Send it to your own tools

    The Signal API returns launch signals for any list of companies as JSON, for your CRM, warehouse or app.

  3. Try it free

    Sign up and spend your free credits on the companies you sell to.

    Start Free1,000 free credits

The API returns more than this page shows

This page shows a preview. The full news record in the Signal API and MCP can also have these 8 fields. Some fields are empty for some signals.

Company

  • linkedin_urlValue in the API
  • industriesValue in the API
  • employee_count_lowValue in the API
  • employee_count_highValue in the API
  • revenueValue in the API
  • descriptionValue in the API

Signal

  • signal_nameValue in the API
  • associationValue in the API
Show the full JSONThe record on this page and the API request

GET /v1/signals/bfa725e4-8404-4920-a629-0854b0693963 returns this record as JSON. POST /v1/companies/enrich returns every signal for vercel.com.

{
  "signal_id": "bfa725e4-8404-4920-a629-0854b0693963",
  "signal_type": "news",
  "signal_subtype": "launches",
  "detected_at": "2026-06-17T17:22:51+00:00",
  "company": {
    "name": "Vercel",
    "domain": "vercel.com"
  },
  "data": {
    "url": "https://www.marktechpost.com/2026/06/17/vercel-releases-eve",
    "title": "Vercel releases eve: an open-source AI agent framework where each agent is a directory of files mapped to capabilities.",
    "excerpt": "Vercel releases eve: an open-source AI agent framework where each agent is a directory of files mapped to capabilities.\n\nJune 17, 2026\n\nVercel has released eve, an open-source framework for building, running, and scaling agents. The project is published as the npm package eve, licensed under Apache-2.0.\n\nBuilding an agent should mean defining what it does. It should not mean assembling all the plumbing that an agent needs to run in production.\n\neve is the framework Vercel builds and runs its own agents on. According to Vercel post, it runs more than a hundred agents in production today.\n\nWhat is eve?\n\neve is a filesystem-first framework for durable backend agents. You create an agent as a directory on disk. The directory is the contract.\n\nEach file describes one component of the agent. At a glance, the tree shows what an agent is and does. It also shows where it lives and when it acts on its own.\n\nThe smallest agent that runs is two files. One sets the model. The other sets the instructions.\n\n// agent/agent.ts import {defineAgent} from \"eve\"; export default defineAgent({ model: \"anthropic/claude-opus-4.8\",});\n\nThe model is one line, and provider fallbacks are supported through AI Gateway. The instructions.md file becomes the system prompt that eve puts in front of every model call.\n\nAn agent is a directory.\n\nVercel's core idea is that agents have a shape. Every team kept...",
    "product": "eve, an open-source framework for building, running, and scaling agents",
    "summary": "Vercel Inc. launched eve, an open-source framework for building, running, and scaling agents on Jun 17th '26.",
    "planning": false,
    "image_url": "https://www.marktechpost.com/wp-content/uploads/2026/06/blog191-10.png",
    "confidence": 0.9679,
    "product_data": {
      "full_text": "eve, an open-source framework for building, running, and scaling agents",
      "fuzzy_match": true
    },
    "published_at": "2026-06-17T17:22:51Z",
    "effective_date": "2026-06-17",
    "article_sentence": "Vercel has released eve, an open-source framework for building, running, and scaling agents."
  }
}

Long text fields are shortened on this page.

Looking up one signal by its id is free. Enrich costs 2 credits per signal returned; a call with no results is free.