Vercel Just Open-Sourced an Agent Framework Where an Agent Is Just a Directory
Vercel shipped something this week that deserves attention from anyone building AI agents: eve, an open-source agent framework built around a single, simple idea. An agent is a directory of files. Add a file, add a capability. No boilerplate registration. No infrastructure glue.
Released under Apache 2.0 on June 17, eve already has over 1,600 GitHub stars and comes from the team behind Next.js (github.com/vercel/eve).
What "Filesystem-First" Actually Means
In eve, every part of your agent has a conventional location:
my-agent/
└── agent/
├── instructions.md # System prompt, written in Markdown
├── agent.ts # Model and runtime config
├── tools/ # Typed functions the model can call
├── skills/ # Larger procedures loaded on demand
├── channels/ # Slack, Discord, HTTP, cron
└── schedules/ # Recurring cron jobs
Add a TypeScript file to tools/, and the filename becomes the tool name. No registry. No wiring. The framework discovers the directory structure at build time and compiles it into a running agent.
Most agent frameworks require registering tools in a central config, keeping registries in sync, and managing the mapping between files and what the agent can call. Eve eliminates that class of problem entirely.
Production Comes Built In
The more significant decision is bundling production infrastructure into the framework itself.
Every agent gets durable execution (sessions checkpoint every step, survive crashes and deploys), sandboxed compute (isolated VMs for code execution), human-in-the-loop approvals, subagents, and built-in evaluations — without the developer assembling these pieces separately.
Vercel describes eve as "Next.js for agents," and the comparison is apt. Next.js succeeded because it made the right production decisions by default — routing, rendering, optimization — so developers could focus on building. Eve does the same for agents: durability, sandboxing, and multi-channel delivery are framework concerns, not per-project assembly tasks.
Production Numbers, Not Demos
Vercel runs over 100 agents internally on eve, including a data-analysis agent handling tens of thousands of Slack queries per month and a support agent that autonomously resolves 92% of tickets. Those are production numbers.
The framework works with any model via Vercel AI Gateway (with provider fallbacks), any MCP server, and deploys with vercel deploy as an ordinary Vercel project. Support for other platforms is planned.
The agent framework landscape has filled up quickly — LangGraph, Mastra, CrewAI, Inngest AgentKit all compete for developers. Eve's differentiator is the filesystem-first design paired with built-in production durability. If you already deploy on Vercel, the integration is seamless.
What This Means If You Use ClawWorld
Eve is a framework for building agents from scratch. ClawWorld takes the other path: you get a persistent agent that's already built, and you install skills on top of it. One command, one capability.
Both approaches share the same belief: the useful AI agent isn't a chat interface. It's a system that takes actions, survives interruptions, and produces real output. Eve demonstrates that the infrastructure layer for agents is ready — durability, sandboxing, and multi-channel delivery are no longer things you build yourself. They're things you expect the framework to provide.
ClawWorld gives you that without the framework assembly step. If you want to build custom agents from the ground up, eve is worth a serious look. If you want an agent that works today, with skills you can install and modify without managing infrastructure, that's what ClawWorld is for.