Startup Ideas Bank

Building agents from filesystem sounds cool but it's still an unproven science project.

AI roast score: 62/100 (C)

The idea

Making AI agent frameworks filesystem-first is like putting a racing spoiler on a tricycle—cool but impractical without real users.

In the founder's own words

vercel/eve — The Framework for Building Agents

eve





eve is a filesystem-first framework for durable AI agents. Core agent capabilities live in
conventional locations, so projects are easier to inspect, extend, and operate.

The filesystem is the authoring interface

A typical eve agent has this structure:

my-agent/
└── agent/
├── agent.ts # Optional: model and runtime config
├── instructions.md # Required: the always-on system prompt
├── tools/ # Optional: typed functions the model can call
│ └── get_weather.ts
├── skills/ # Optional: procedures loaded on demand
│ └── plan_a_trip.md
├── channels/ # Optional: message channels (HTTP, Slack, Discord)
│ └── slack.ts
└── schedules/ # Optional: recurring cron jobs
└── weekly_recap.ts

Read the documentation for the full project layout and guides.

Quick start

npx eve@latest init my-agent

This creates a new my-agent directory, installs its dependencies, initializes Git, and starts
the interactive terminal UI.

To add eve to an existing project, pass a path:

cd myapp
npx eve@latest init .

Note
The eve package includes its full documentation, so coding agents can read it locally from
node_modules/eve/docs .

A minimal example

The generated project includes an agent directory. Replace agent/instructions.md with:

You are a concise weather demo assistant. Tell users that the weather data is mocked.

Add a mock weather tool at agent/tools/get_weather.ts :

import { defineTool } from "eve/tools" ;
import { z } from "zod" ;

export default defineTool ( {
description : "Return mock weather data for a city." ,
inputSchema : z . object ( { city : z . string ( ) . min ( 1 ) } ) ,
async execute ( { city } ) {
return { city , condition : "Sunny" , temperatureF : 72 } ;
} ,
} ) ;

Choose the model in agent/agent.ts :

import { defineAgent } from "eve" ;

export default defineAgent ( {
model : "anthropic/claude-sonnet-4.6" ,
} ) ;

For a new scaffold, start the agent again:

npm run dev

That's a working agent. Add human-in-the-loop prompts, subagents, and schedules as needed.
Follow the first-agent tutorial for a complete
walkthrough.

Community

The eve community lives on GitHub Discussions ,
where you can ask questions, share ideas, and show what you've built.

Contributing

Contributions are welcome. See CONTRIBUTING.md to get the repo
running locally and land a change, and use
issues and
discussions to collaborate. By
participating, you agree to our Code of Conduct .

Security

Please do not open public issues for security vulnerabilities. Instead, follow
SECURITY.md and report responsibly to
responsible.disclosure@vercel.com .

Beta terms

eve is currently in beta and subject to the Vercel beta terms ;
the framework, APIs, document

The roast

Your 'filesystem-first' approach to building AI agents feels more like a developer's weekend hobby than a viable business. The concept is geeky but who really needs this? Your target audience is 'general' and your biggest unknown is 'will_pay'—not a great combo. Plus, no funding, solo founder, and still in the idea stage? You're miles away from being market-ready. Red flags are popping up everywhere: a solo founder tackling a complex tech problem, no clear evidence of market demand, and you're at the idea stage with no funding.

Red flags

Verdict

You need to prove someone will actually pay for this, and fast.

Start with your own startup idea →

More ideas roasted by AI

Browse all startup ideas →