Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions docs.json
Original file line number Diff line number Diff line change
Expand Up @@ -71,6 +71,7 @@
"docs/agents/pi",
"docs/agents/deep-agents",
"docs/agents/open-swe",
"docs/agents/eve",
"docs/agents/google-adk",
"docs/agents/mastra",
"docs/agents/openai-agents-sdk",
Expand Down
228 changes: 228 additions & 0 deletions docs/agents/eve.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,228 @@
---
title: "Vercel Eve"
description: "Run Vercel Eve agent sandboxes on E2B with the @e2b/eve-sandbox backend."
icon: "/images/icons/vercel-eve.svg"
---

[Vercel Eve](https://vercel.com/docs/eve) is a filesystem-first framework for durable backend AI agents: you author an agent as files under `agent/`, and Eve compiles them into an app that runs on Vercel Functions. Every Eve agent has exactly one [sandbox](https://eve.dev/docs/sandbox) — the isolated bash environment rooted at `/workspace` that backs the built-in `bash`, `read_file`, `write_file`, `glob`, and `grep` tools.

The [`@e2b/eve-sandbox`](https://github.com/e2b-dev/eve-sandbox) package is an E2B backend for that sandbox — the E2B counterpart to Eve's built-in `vercel()`, `docker()`, `microsandbox()`, and `justbash()` backends. It implements the public `SandboxBackend` interface from `eve/sandbox`, so Eve itself needs no changes and no fork.

<Note>
`@e2b/eve-sandbox` is experimental, and Eve is in beta. Both APIs may change.
</Note>

## Why E2B as the backend

| | E2B backend | Eve's local backends |
| --- | --- | --- |
| Where it runs | E2B cloud microVMs, from local dev and production alike | Docker daemon, local VM, or a simulated shell on the host |
| Startup | ~150 ms from a snapshot or [custom template](/docs/template/quickstart) | Image pull / VM boot on the developer machine |
| Environment | Any [E2B template](/docs/template/quickstart) you build | Eve's `ghcr.io/vercel/eve` image, or a Docker image you supply |
| Persistence | [Auto-pause and resume](/docs/sandbox/persistence) — filesystem survives days of idle | Container/VM tied to the machine that started it |
| Egress control | E2B firewall: domain allow-lists and header injection | Domain policies on `vercel()`/`microsandbox()`; `docker()` is all-or-nothing |

Use it when you want the same sandbox behavior in local dev, CI, and production, on infrastructure you control the image for.

## Prerequisites

- Node.js 22 or later
- An Eve project (`npx eve@latest init my-agent`)
- An [E2B API key](https://e2b.dev/dashboard?tab=keys)

## Install

```bash
npm i @e2b/eve-sandbox e2b
```

`eve` (>= 0.27) and `ai` (>= 7) are peer dependencies already present in an Eve project.

Set your key — the backend reads `E2B_API_KEY` unless you pass `apiKey`:

```bash
export E2B_API_KEY="e2b_***"
```

## Configure the backend

Author `defineSandbox` and pass `e2b()` as the backend:

```typescript title="agent/sandbox.ts"
import { defineSandbox } from 'eve/sandbox'
import { e2b } from '@e2b/eve-sandbox'

export default defineSandbox({
backend: () => e2b({ template: 'base' }),
})
```

That is the whole integration. The agent's `bash` tool now runs commands in an E2B sandbox, its file tools read and write the sandbox filesystem, and nothing executes on your app runtime.

Prefer the **factory form** (`backend: () => e2b({...})`) over `backend: e2b({...})`: it defers reading environment variables until first use and memoizes the backend, so its prewarmed-snapshot cache survives across calls.

Use the folder layout (`agent/sandbox/sandbox.ts`) instead if you also seed files from `agent/sandbox/workspace/**`.

## Run the agent

```bash
pnpm dev # or: npx eve dev
```

Ask the agent to run a command and it executes in a real E2B sandbox. Sandboxes created this way appear in your [E2B dashboard](https://e2b.dev/dashboard).

## Bootstrap and per-session setup

Eve has two lifecycle hooks, and the E2B backend maps each onto a different E2B primitive:

```typescript title="agent/sandbox/sandbox.ts"
import { defineSandbox } from 'eve/sandbox'
import { e2b } from '@e2b/eve-sandbox'

export default defineSandbox({
backend: () =>
e2b({
template: 'base',
timeoutMs: 30 * 60 * 1000,
envs: { NODE_ENV: 'production' },
}),

// Build time, once per template — baked into a reusable E2B snapshot.
async bootstrap({ use }) {
const sandbox = await use()
await sandbox.run({ command: 'sudo apt-get install -y jq' })
},

// Once per durable session — tighten egress for the turn.
async onSession({ use }) {
await use({ networkPolicy: { allow: ['*.npmjs.org', 'github.com'] } })
},
})
```

- **`bootstrap`** runs during Eve's build-time `prewarm()`. The backend creates a sandbox, runs your bootstrap, writes your `workspace/` seed files, then captures an **E2B snapshot**. Later sessions fork that snapshot, so installs are paid once, not per session.
- **`onSession`** runs once per durable session against a live sandbox, and is the right place for network policy, per-user credentials, and one-time markers.

Snapshots are named from Eve's `templateKey` (which tracks your authored sandbox source, seed contents, and `revalidationKey`) plus a hash of the snapshot-affecting backend options — base template, baked `envs`, and network policy. Change any of those and the next build captures a fresh snapshot instead of reusing a stale one.

## Session persistence

E2B sandboxes are created with `lifecycle: { onTimeout: 'pause', autoResume: true }`, and the default timeout is **30 minutes** (E2B's own 5-minute default would expire mid-turn). On timeout the sandbox [pauses rather than dies](/docs/sandbox/persistence): the filesystem is preserved and the next message resumes it.

On the next turn the backend reattaches in this order:

1. The `sandboxId` persisted by Eve for that session.
2. A still-running or paused sandbox whose E2B metadata matches `eveBackend: "e2b"` and the session's `eveSessionKey`.
3. Otherwise a fresh sandbox, forked from the prewarmed snapshot.

Two consequences worth knowing:

- **The backend's `shutdown()` is intentionally a no-op.** Killing the sandbox on server shutdown would drop background work and force Eve to recreate it without rerunning `onSession`. Sandboxes are left paused and expire on their own — kill them from the [dashboard](https://e2b.dev/dashboard) or the [SDK](/docs/sandbox) if you want them gone sooner. Opt out with `autoPause: false` to kill on timeout instead.
- **Reconnects do not re-apply the configured `networkPolicy`.** A resumed sandbox keeps its live policy, including any tightening `onSession` applied. Re-stamping the create-time default could silently loosen a locked-down session.

## Network policy

Egress rules go on the factory (applied to each fresh session, before authored `bootstrap` runs) or in `onSession`'s `use()`. The backend translates Eve's `SandboxNetworkPolicy` into an [E2B firewall](/docs/network/internet-access) update:

| Eve policy | E2B update |
| --- | --- |
| `"allow-all"` (default) | `allowInternetAccess: true` |
| `"deny-all"` | `allowInternetAccess: false` |
| `{ allow: ['github.com', '*.npmjs.org'] }` | `allowOut: [...]` + `denyOut: ['0.0.0.0/0']` |
| `{ allow: ['*'], subnets: { deny: ['10.0.0.0/8'] } }` | `denyOut: ['10.0.0.0/8']` |
| `{ allow: [] }` | `allowInternetAccess: false` |

Restricting egress to an allow-list requires the catch-all in `denyOut` — E2B gives allow rules absolute precedence over deny rules, so the listed hosts pass and everything else is blocked. The backend adds that for you.

<Warning>
Because allow beats deny in E2B, some Eve policies cannot be expressed faithfully. The backend **throws instead of silently weakening them**:

- `subnets.deny` combined with an allow-list — the "denied" hosts would stay reachable. Use `{ allow: ['*'], subnets: { deny: [...] } }` for deny-lists, or drop `subnets.deny` (anything outside an allow-list is already blocked).
- A per-rule `match` condition — E2B applies header transforms to every request to a host.
- `forwardURL` request proxying — no E2B equivalent.
- A header `transform` alongside a catch-all `"*"` allow — a transform host must be allow-listed, which an allow-all cannot also be.
</Warning>

### Credential brokering

E2B can inject a header at the firewall so a secret authenticates egress without ever entering the sandbox. Eve expresses this as a per-domain `transform`:

```typescript
async onSession({ use }) {
await use({
networkPolicy: {
allow: {
'github.com': [{ transform: [{ headers: { authorization: 'Basic your_base64_credentials_here' } }] }],
'api.example.com': [],
},
},
})
}
```

List every host explicitly. Eve's documented `"*": []` catch-all pattern is rejected by this backend for the reason above — pair transforms with an explicit allow-list instead.

To change policy mid-turn, call `sandbox.setNetworkPolicy(...)` on the live handle from any authored tool.

## Custom templates

`template` accepts any E2B template ID or alias. Build a [custom template](/docs/template/quickstart) with your runtimes, system packages, and toolchain pre-installed, and every session starts from it:

```typescript
export default defineSandbox({
backend: () => e2b({ template: 'your-template-id-or-name' }),
})
```

Templates and snapshots compose: the template is the base image, and Eve's `bootstrap` layers your agent-specific setup into a snapshot on top of it. Put slow, stable work (compilers, system packages) in the template; put agent-specific work (cloning a baseline repo, installing project dependencies) in `bootstrap`.

## Backend options

```typescript
e2b({
template: 'base', // E2B template ID or alias
timeoutMs: 30 * 60 * 1000, // auto-pause timeout; default 30 minutes
envs: { NODE_ENV: 'production' }, // env vars baked into every sandbox
metadata: { team: 'growth' }, // E2B metadata, create-time only
tags: { tier: 'beta' }, // diagnostic tags, merged into metadata
apiKey: process.env.E2B_API_KEY, // defaults to E2B_API_KEY
domain: 'e2b.dev', // self-hosted or region endpoint
networkPolicy: 'allow-all', // initial policy for each fresh session
autoPause: true, // false → kill on timeout instead of pause
createOptions: {}, // raw E2B SandboxOpts escape hatch
})
```

`createOptions` is merged into every `Sandbox.create()` call, so anything the [E2B JavaScript SDK](/docs/sdk-reference/js-sdk) supports is reachable even when this backend has no dedicated option for it. Explicit options win over `createOptions`.

## How the integration works

| Component | Responsibility |
| --- | --- |
| Eve runtime | Runs turns, owns durable session state, calls the backend's `prewarm` and `create` |
| `defineSandbox` | Declares the backend plus the `bootstrap` and `onSession` hooks |
| `e2b()` backend | Creates, reconnects, and configures E2B sandboxes; maps network policy |
| E2B snapshot | Captures bootstrap + seed files once, forked per session |
| E2B template | Base OS, runtimes, and pre-installed dependencies |

Paths line up because the backend anchors relative paths to `/workspace`, Eve's cross-backend namespace — E2B's own default working directory is `/home/user`, and the backend creates `/workspace` during base setup. Every E2B API call this backend makes is tagged with an `eve-sandbox/<version>` integration identifier.

## Learn more

- [`@e2b/eve-sandbox` on GitHub](https://github.com/e2b-dev/eve-sandbox) — source, unit tests, and a runnable Next.js example
- [Eve sandbox documentation](https://eve.dev/docs/sandbox) — session handle API, lifecycle hooks, and backends
- [Eve on Vercel](https://vercel.com/docs/eve) — how Eve maps onto Vercel Functions, Workflows, and AI Gateway

## Related guides

<CardGroup cols={3}>
<Card title="Templates" icon="layer-group" href="/docs/template/quickstart">
Build custom sandbox templates with pre-installed dependencies
</Card>
<Card title="Sandbox persistence" icon="clock" href="/docs/sandbox/persistence">
Auto-pause, resume, and manage sandbox lifecycle
</Card>
<Card title="Internet access" icon="shield" href="/docs/network/internet-access">
Restrict sandbox egress with domain allow-lists
</Card>
</CardGroup>
9 changes: 9 additions & 0 deletions images/icons/vercel-eve.svg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading