Skip to content
Back to search

eve

The Open Framework for Building Agents

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/vercel/eve with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/vercel/eve'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/vercel-eve/badge.svg)](/listings/vercel-eve)

HTML

<a href="/listings/vercel-eve"><img src="/api/listings/vercel-eve/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

npx eve@latest init my-agent

This creates a new `my-agent` directory, installs its dependencies, initializes Git, and starts the interactive terminal UI. The generated agent uses `openai/gpt-6-luna-fast` with high reasoning.

To start with another AI Gateway model, pass its model ID:

npx eve@latest init my-agent --model openai/gpt-5.6-terra

Passing `--model` without `--reasoning` uses the provider's default reasoning. Pass `--reasoning` to set it explicitly.

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: "openai/gpt-6-luna-fast",
  reasoning: "high",
});

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](https://eve.dev/docs/tutorial/first-agent) for a complete walkthrough.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 142 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <div align="center">
  2. <a href="https://eve.dev/">
  3. <picture>
  4. <source media="(prefers-color-scheme: dark)" srcset=".github/assets/eve.svg">
  5. <img alt="eve logo" src=".github/assets/eve.svg" height="128">
  6. </picture>
  7. </a>
  8. <h1>eve</h1>
  9. <a href="https://vercel.com"><img alt="Vercel logo" src="https://img.shields.io/badge/MADE%20BY%20Vercel-000000.svg?style=for-the-badge&logo=Vercel&labelColor=000"></a>
  10. <a href="https://www.npmjs.com/package/eve"><img alt="NPM version" src="https://img.shields.io/npm/v/eve.svg?style=for-the-badge&labelColor=000000"></a>
  11. <a href="https://github.com/vercel/eve/blob/main/LICENSE"><img alt="License" src="https://img.shields.io/npm/l/eve.svg?style=for-the-badge&labelColor=000000"></a>
  12. <a href="https://github.com/vercel/eve/discussions"><img alt="Join the community on GitHub" src="https://img.shields.io/badge/Join%20the%20community-blueviolet.svg?style=for-the-badge&logo=Github&labelColor=000000&logoWidth=20"></a>
  13. </div>
  14. [eve](https://eve.dev/) is a filesystem-first framework for durable AI agents. Core agent capabilities live in
  15. conventional locations, so projects are easier to inspect, extend, and operate.
  16. ## The filesystem is the authoring interface
  17. A typical eve agent has this structure:
  18. ```text
  19. my-agent/
  20. └── agent/
  21. ├── agent.ts # Optional: model and runtime config
  22. ├── instructions.md # Required: the always-on system prompt
  23. ├── tools/ # Optional: typed functions the model can call
  24. │ └── get_weather.ts
  25. ├── skills/ # Optional: procedures loaded on demand
  26. │ └── plan_a_trip.md
  27. ├── channels/ # Optional: message channels (HTTP, Slack, Discord)
  28. │ └── slack.ts
  29. └── schedules/ # Optional: recurring cron jobs
  30. └── weekly_recap.ts
  31. ```
  32. Read the [documentation](https://eve.dev/docs) for the full project layout and guides.
  33. ## Quick start
  34. ```bash
  35. npx eve@latest init my-agent
  36. ```
  37. This creates a new `my-agent` directory, installs its dependencies, initializes Git, and starts
  38. the interactive terminal UI. The generated agent uses `openai/gpt-6-luna-fast` with high reasoning.
  39. To start with another AI Gateway model, pass its model ID:
  40. ```bash
  41. npx eve@latest init my-agent --model openai/gpt-5.6-terra
  42. ```
  43. Passing `--model` without `--reasoning` uses the provider's default reasoning. Pass `--reasoning` to set it explicitly.
  44. To add eve to an existing project, pass a path:
  45. ```bash
  46. cd myapp
  47. npx eve@latest init .
  48. ```
  49. > [!NOTE]
  50. > The `eve` package includes its full documentation, so coding agents can read it locally from
  51. > `node_modules/eve/docs`.
  52. ### A minimal example
  53. The generated project includes an `agent` directory. Replace `agent/instructions.md` with:
  54. ```md
  55. You are a concise weather demo assistant. Tell users that the weather data is mocked.
  56. ```
  57. Add a mock weather tool at `agent/tools/get_weather.ts`:
  58. ```ts
  59. import { defineTool } from "eve/tools";
  60. import { z } from "zod";
  61. export default defineTool({
  62. description: "Return mock weather data for a city.",
  63. inputSchema: z.object({ city: z.string().min(1) }),
  64. async execute({ city }) {
  65. return { city, condition: "Sunny", temperatureF: 72 };
  66. },
  67. });
  68. ```
  69. Choose the model in `agent/agent.ts`:
  70. ```ts
  71. import { defineAgent } from "eve";
  72. export default defineAgent({
  73. model: "openai/gpt-6-luna-fast",
  74. reasoning: "high",
  75. });
  76. ```
  77. For a new scaffold, start the agent again:
  78. ```bash
  79. npm run dev
  80. ```
  81. That's a working agent. Add human-in-the-loop prompts, subagents, and schedules as needed.
  82. ### Add Web Chat
  83. From your agent's directory, link a Vercel project and add Web Chat:
  84. ```bash
  85. npx eve link
  86. npx eve add channel/web
  87. ```
  88. Choose a hosting layout, then **Sign in with Vercel** to provision authentication for members of the project's team.
  89. You can also select **Web Chat** from the terminal UI's `/add` channel picker.
  90. Run `npx eve deploy` when ready to publish. Local development works without browser sign-in.
  91. See the [Web Chat setup guide](https://eve.dev/docs/channels/eve#web-chat-with-sign-in-with-vercel) for permissions and recovery.
  92. ## Community
  93. The eve community lives on [GitHub Discussions](https://github.com/vercel/eve/discussions),
  94. where you can ask questions, share ideas, and show what you've built.
  95. ## Contributing
  96. Contributions are welcome. See [CONTRIBUTING.md](CONTRIBUTING.md) to get the repo
  97. running locally and land a change, and use
  98. [issues](https://github.com/vercel/eve/issues) and
  99. [discussions](https://github.com/vercel/eve/discussions) to collaborate. By
  100. participating, you agree to our [Code of Conduct](CODE_OF_CONDUCT.md).
  101. ## Security
  102. Please do not open public issues for security vulnerabilities. Instead, follow
  103. [SECURITY.md](SECURITY.md) and report responsibly to
  104. [responsible.disclosure@vercel.com](mailto:responsible.disclosure@vercel.com).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.