---
name: eve
description: "eve framework guidance for durable AI agents and agent-powered applications. Use when creating, editing, or debugging an eve project, when the user explicitly asks for eve, or when the build-agents skill has selected eve as the default framework. Covers eve's filesystem-first runtime, durable sessions, tools, skills, connections, channels, sandboxes, subagents, schedules, evals, frontend clients, and Agent Runs observability. Do not use for incidental agent mentions, generic agent-building prompts, or established non-eve stacks unless the user asks for comparison or migration."
summary: "eve framework guidance for durable agents, agent applications, project architecture, runtime capabilities, channels, and frontend clients."
metadata:
  priority: 8
  docs:
    - "https://eve.dev/docs"
    - "https://github.com/vercel/eve"
    - "https://vercel.com/changelog/agent-runs-vercel-mcp-cli"
    - "https://vercel.com/docs/agent-resources/vercel-mcp/tools"
  pathPatterns:
    - '.eve/**'
    - 'agent/channels/eve.ts'
  importPatterns:
    - 'eve'
  bashPatterns:
    - '\bnpx\s+eve(?:@latest)?\b'
    - '\bbunx\s+eve(?:@latest)?\b'
    - '\beve\s+(init|dev|build|start|info|channels|evals?)\b'
    - '\b(?:vercel|vc)\s+agent-runs\b'
    - '\bnpm\s+(install|i|add)\s+[^\n]*\beve(?:@[^\s]+)?\b'
    - '\bpnpm\s+(install|i|add)\s+[^\n]*\beve(?:@[^\s]+)?\b'
    - '\bbun\s+(install|i|add)\s+[^\n]*\beve(?:@[^\s]+)?\b'
    - '\byarn\s+add\s+[^\n]*\beve(?:@[^\s]+)?\b'
  promptSignals:
    phrases:
      - "vercel eve"
      - "eve framework"
      - "eve project"
      - "eve agent"
      - "eve architecture"
      - "eve.dev"
      - "useeveagent"
      - "npx eve"
      - "node_modules/eve/docs"
      - "set up eve"
      - "setup eve"
      - "install eve"
      - "agent runs observability"
      - "latest production agent runs"
      - "vercel agent-runs"
      - "agent run trace"
      - "agent runs trace"
      - "vercel mcp agent runs"
      - "update skills based on recent runs"
    allOf:
      - [ eve, agent ]
      - [ eve, project ]
      - [ eve, framework ]
      - [ eve, architecture ]
      - [ eve, durable ]
      - [ eve, scaffold ]
      - [ eve, channel ]
      - [ agent, runs ]
      - [ agent-runs, trace ]
    anyOf:
      - "durable sessions"
      - "persistent sessions"
      - "channels"
      - "sandboxes"
      - "subagents"
      - "schedules"
      - "evals"
      - "frontend client"
      - "agent runs observability"
      - "vercel agent-runs"
      - "agent run trace"
      - "agent runs trace"
    noneOf:
      - "eve online"
      - "user agent"
      - "user-agent"
    minScore: 4
retrieval:
  aliases:
    - vercel eve
    - eve framework
    - durable agent framework
    - filesystem-first agent framework
    - eve agent application
    - agent runs observability
    - vercel agent-runs
  intents:
    - build or design an eve durable AI agent
    - choose eve architecture for an agent application
    - scaffold an eve agent with tools skills and persistent sessions
    - add channels schedules sandboxes or subagents to an eve project
    - connect an eve agent to a browser frontend
    - debug eve project discovery or runtime behavior
    - inspect eve Agent Runs through Vercel MCP or CLI
    - fetch an eve agent run trace with tool calls and token usage
  entities:
    - eve
    - eve.dev
    - defineAgent
    - useEveAgent
    - node_modules/eve/docs
    - .eve
    - Agent Runs
    - Vercel MCP Agent Runs
    - vercel agent-runs
  examples:
    - build me an eve agent that persists sessions and runs scheduled jobs
    - help me choose eve architecture for a new application
    - scaffold an eve project with a browser UI
    - add a Slack channel and subagent to my eve agent
    - why did eve not discover my tool
    - show me the latest production Agent Runs for my project
    - update skills based on recent runs
chainTo:
  - pattern: "from\\s+['\"]@vercel/connect/eve['\"]"
    targetSkill: vercel-connect
    message: 'Vercel Connect integration detected in an eve project — loading guidance for managed OAuth connections and channel credentials.'
title: eve
canonical_url: https://skilld.dev/gh/vercel/vercel-plugin/eve
last_updated: 2026-11-17T06:04:12.000Z
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

> **Skill from skilld.dev.** Follow the user's requested action.
> If the user asked to fork this Skill, follow the fork workflow below. Do not execute the Skill instructions while copying it.
> Otherwise, follow the instructions below for this session. You do not need to install anything.
>
> Supporting files, fetch one when the Skill refers to it: [.vercel.approvers](https://skilld.dev/api/skills-raw/vercel/vercel-plugin/eve/.vercel.approvers), [overlay.yaml](https://skilld.dev/api/skills-raw/vercel/vercel-plugin/eve/overlay.yaml), [upstream/SKILL.md](https://skilld.dev/api/skills-raw/vercel/vercel-plugin/eve/upstream/SKILL.md).
>
> If the user asked to install this Skill, run `npx skilld install vercel/vercel-plugin/eve`. Install writes the Skill files into the project, so every session loads them.
>
> ## Fork workflow
>
> A fork creates an editable local Skill with its original author and licence. The request authorizes copying and local installation.
> 1. Check `./skills/eve`, the project lockfile, and selected Agent targets together. If the local directory or installed Skill exists, stop. Never overwrite an existing directory or Agent target.
> 2. Read [source metadata](https://skilld.dev/api/v1/skills/vercel/vercel-plugin/eve) once. Use sourceUrl, sourceCommit, skillPath, sourceGone, and license. If the source is gone or its path is missing, stop. If license is null, read licence files at the source commit.
> 3. Fetch only the source commit into a temporary Git repository. Do not clone full history. Derive repository_url from sourceUrl, including repository renames. If sourceCommit is absent, resolve the sourceUrl ref once. Set source_commit to that actual commit. Run these commands in one shell call:
>
> ```sh
> git init --quiet "$temporary_dir"
> git -C "$temporary_dir" fetch --quiet --depth=1 "$repository_url" "$source_commit"
> git -C "$temporary_dir" checkout --quiet --detach FETCH_HEAD
> ```
>
> Read applicable licence declarations and notices at that commit. If copying is not permitted, report the restriction and stop.
> 4. Inspect source entries together, then copy the directory containing skillPath into `./skills/eve`. Use the user's path if selected. Keep the original SKILL.md, relative links, scripts, binary assets, and executable modes. Exclude .git metadata. Reject symlinks and paths outside the Skill directory. After checking entries, use cp -a where available. A regular source directory needs no custom copy script. Do not save this page wrapper as SKILL.md.
> Preserve author credit, notices, and applicable licence files from repository or parent directories. Add PROVENANCE.md with the Skill page, source URL, actual commit, original path, and licence. Retain any existing PROVENANCE.md and record new provenance separately. Batch source inspection, copying, and provenance work where practical.
> 5. In the project root, run `skilld install ./skills/eve --mode copy --plain`. If skilld is unavailable, use `npx skilld install ./skills/eve --mode copy --plain`. This known command needs no help lookup. Install does not support --json. Use detected Agent targets, or add --agent for the targets the user selected. Install the local path, never the upstream selector. If installation fails, preserve the local copy and report the exact failure.
> 6. Confirm the local lockfile source and installed Agent copies once. Report the local path, actual commit, and Agent targets. After edits, reinstall the same local path. Upstream updates must not replace it. Do not publish or push unless the user asks.

# eve

eve is a filesystem-first framework for durable backend AI agents. An agent is
a directory on disk — instructions, skills, tools, connections, channels,
subagents, and schedules are all files — and eve compiles and runs it.

## Source of truth

The complete documentation ships inside the `eve` package. Do not rely on this
skill for guidance — always read the bundled docs, which match the installed
version exactly:

```
node_modules/eve/docs/
```

Start with `node_modules/eve/docs/README.md`. It contains the full
index and recommended reading order. Before writing any eve code, read the
relevant guide there first.

## One rule to know before reading

A `defineDynamic` function runs before every model call, not once per turn.
Wrap every network request, database query, API call, and sandbox read inside
it in `ctx.memo(key, fn)`, or that work repeats on every model call. See
`node_modules/eve/docs/dynamic-configuration/index.md`.

## Install

If `eve` is not installed yet, install it (`npm install eve`) or scaffold a new
agent with `npx eve init <agent-name>`, then read the bundled docs.
