---
title: "Guild vs Vercel eve"
description: "Guild vs Vercel eve: building, integrations, credentials, triggers, and approvals compared, plus how to move an eve agent to Guild."
canonical: "https://www.guild.ai/compare/vercel-eve"
---

# Guild vs Vercel eve

Guild vs Vercel eve: building, integrations, credentials, triggers, and approvals compared, plus how to move an eve agent to Guild.

eve is Vercel's open-source TypeScript framework for long-running agents, which you deploy on Vercel or host yourself. Guild runs agents for you, built several ways, keeps secrets out of agent code, and shares them on a public Agent Hub. An eve agent maps closely to a Guild TypeScript agent.

Last verified 2026-10-30. Across 35 features, Guild leads on 9, Vercel eve on 7, and 19 are level. Every cell below names its source.

## When to choose Vercel eve

- You want an open-source framework (Apache-2.0) you can host yourself.
- Your team already ships on Vercel and wants agents billed in the same place.
- You need per-tool approval rules (always, once, or automatic) today.
- You want cron schedules in files, or channels like Teams, Telegram, or iMessage, out of the box.

## When to choose Guild

- You want agents run for you, with no direct network access and secrets kept out of agent code.
- You need each agent to get only the access it needs, down to single actions.
- Your team builds agents more than one way: TypeScript, plain instructions, Goose, OpenClaw, or LangGraph.
- You want to share, version, and reuse agents on a public Agent Hub.
- You want one CLI from first build to publish, with triggers and integrations.

## What Vercel eve and Guild are

**Vercel eve.** In eve, each part of an agent lives in its own folder: instructions, tools, connections, channels, schedules, sub-agents, and a sandbox. It deploys to Vercel Functions, Workflows, and Sandbox, adds per-tool approvals, evals, and run tracing, and is open source (Apache-2.0). It's in beta.

**Guild.** Guild runs the agent for you and gives you control over it: secrets stay out of agent code, you decide which actions it can take, and you get workspaces, audit, and versions on the Agent Hub. Write the same agent in TypeScript, or as an OpenClaw workspace when it needs shell and git.

|   | Vercel eve | Guild |
| --- | --- | --- |
| Category | Open-source TypeScript agent framework | One platform to run and control AI agents |
| License | Apache-2.0 | Proprietary platform; CLI published on npm as @guildai/cli |
| Pricing | Framework is free; you pay for the Vercel resources it uses | No public price list; plans priced with the Guild team; model usage metered at list price |
| Maturity | Beta / public preview (announced 2026-06-17) | Generally available |
| Docs | https://eve.dev/docs | https://docs.guild.ai |

## Concept map: Vercel eve to Guild

| Concept | Vercel eve | Guild | Note |
| --- | --- | --- | --- |
| The agent | `agent/agent.ts` with `defineAgent({ model })` | `agent.ts` with `agent({ description, inputSchema, outputSchema, tools, run })` or `llmAgent()` |   |
| System prompt | `agent/instructions.md` | The `llmAgent` system prompt, or `PROMPT.md` in a Native agent |   |
| Tools | `agent/tools/*.ts` with `defineTool` | The `tools` object in `agent.ts`, with pure helpers in `logic.ts` |   |
| Connections | `agent/connections/` (MCP, OpenAPI) | Guild integrations (`guild integration`, Porter), imported as `@guildai-services/*` packages |   |
| Auth and secrets | Vercel Connect and `getToken` auth | Credentials scoped to an account, workspace, member, or agent, plus credential policies | Secrets stay in the credential proxy. |
| Channels | `agent/channels/` (HTTP, Slack, …) | API and event triggers; channels stay adapters |   |
| Schedules | `agent/schedules/` with `defineSchedule({ cron })` | A schedule trigger: `guild trigger create --type time` | The CLI accepts `--frequency CRON --cron-expression`; the docs list hourly to monthly presets. |
| Sub-agents | `agent/subagents/<name>/` | `guildAgentTool({ calls: 'owner~agent' })`, or `sub_agents` in `guild.yaml` |   |
| Sandbox | `sandbox.ts` with `bash`, `read_file`, `write_file` | The OpenClaw agent type: `AGENTS.md` + `skills/`, with shell, git, and files |   |
| Skills | `agent/skills/` | OpenClaw `skills/<name>/SKILL.md`, or Hub skills |   |
| Approvals | Tool `approval: always()` / `once()` | An approval gate on the same action, set in the Guild UI | Per agent and per action; no code needed. |
| Evals | `evals/**/*.eval.ts` and `eve eval` | `guild agent test` and Guild Evaluations |   |
| Run history | Agent Runs dashboard | Sessions and the session event log |   |
| Deploy | `eve deploy` | `guild agent save --wait --publish` |   |

## Feature by feature: Vercel eve vs. Guild

### Authoring

| Feature | Vercel eve | Guild |
| --- | --- | --- |
| Code-first TypeScript agents | **Yes.** defineAgent and defineTool files under agent/; eve is in Beta, so APIs may still change. ([source](https://vercel.com/docs/eve/concepts), checked 2026-10-23) | **Yes.** @guildai/agents-sdk: agent(), llmAgent(), and the task API (task.llm, task.tools, task.ui, task.gather). ([source](https://docs.guild.ai/packages/agents-sdk.md), checked 2026-10-23) |
| Python / LangGraph agents | **No.** TypeScript only. ([source](https://vercel.com/docs/eve), checked 2026-10-23) | **Yes.** LangGraph agent type: langgraph.json + graph.py using guild_model() and guild_tools(). LangChain v1, Python 3.13, no extra pip packages. ([source](https://docs.guild.ai/guide/agent-types.md), checked 2026-10-23) |
| Instruction-only (no-code) agents | **Partial.** instructions.md is the system prompt, but every agent lives in a code project. ([source](https://eve.dev/docs/reference/agent-files), checked 2026-10-23) | **Yes.** Native agents: PROMPT.md + guild.yaml, no container, ready immediately. ([source](https://docs.guild.ai/guide/agent-types.md), checked 2026-10-23) |
| Several agent formats on one platform | **No.** One format: the eve agent/ file layout. ([source](https://eve.dev/docs/reference/agent-files), checked 2026-10-23) | **Yes.** Native, TypeScript, Goose, OpenClaw, and LangGraph agent types, plus ADK (CLI 0.28). ([source](https://docs.guild.ai/guide/agent-types.md), checked 2026-10-23) |
| Typed agent input/output | **Partial.** Zod inputSchema per tool; agents exchange session messages. ([source](https://eve.dev/docs/tools.md), checked 2026-10-23) | **Yes.** Zod inputSchema and outputSchema on agent(); root input must be z.object. ([source](https://docs.guild.ai/packages/agents-sdk.md), checked 2026-10-23) |
| Repo / workspace agents (shell, git, files) | **Yes.** One Vercel Sandbox per agent with built-in bash, read_file, and write_file tools. ([source](https://vercel.com/docs/eve), checked 2026-10-23) | **Yes.** OpenClaw agents (AGENTS.md + skills/) run in the guildai~lobsterpot container with shell, git, and file editing. ([source](https://docs.guild.ai/guide/agent-types.md), checked 2026-10-23) |
| Sub-agents and agent-to-agent calls | **Yes.** subagents/<name>/agent.ts in the agent directory. ([source](https://eve.dev/docs/reference/agent-files), checked 2026-10-23) | **Yes.** guildAgentTool calls owner~agent; Native, Goose, and OpenClaw agents declare sub_agents in guild.yaml. ([source](https://docs.guild.ai/guide/guild-yaml.md), checked 2026-10-23) |

### Tools & integrations

| Feature | Vercel eve | Guild |
| --- | --- | --- |
| Managed integrations catalog | **Yes.** Registry installs (eve add channel/slack) and Vercel Connect connectors. ([source](https://eve.dev/integrations), checked 2026-10-23) | **Yes.** 37 non-model integrations (GitHub, Slack, Gmail, Linear, Jira, Notion, Zendesk, …) plus 8 model publishers. ([source](https://docs.guild.ai/integrations/overview.md), checked 2026-10-23) |
| Use MCP servers as tools | **Yes.** defineMcpClientConnection in agent/connections/. ([source](https://eve.dev/docs/connections), checked 2026-10-23) | **Yes.** Build custom integrations from MCP servers with guild integration. ([source](https://docs.guild.ai/integrations/overview.md), checked 2026-10-23) |
| Platform exposed over MCP | **Yes.** MCP is one of eve's channels, so agents can be reached from MCP clients. ([source](https://eve.dev/docs/channels/overview.md), checked 2026-10-23) | **Yes.** Guild is an MCP server: https://api.guild.ai/mcp (OAuth + PKCE) or local `guild mcp`. ([source](https://docs.guild.ai/api-reference/mcp.md), checked 2026-10-23) |
| Custom APIs from OpenAPI | **Yes.** defineOpenAPIConnection for OpenAPI 3.x APIs. ([source](https://eve.dev/docs/connections), checked 2026-10-23) | **Yes.** guild integration builds tools from OpenAPI specs; Porter drafts integrations from public APIs. ([source](https://docs.guild.ai/integrations/overview.md), checked 2026-10-23) |
| Secrets never reach the agent | **Yes.** The model never sees URLs or credentials; auth via getToken, headers, or Vercel Connect. ([source](https://eve.dev/docs/connections), checked 2026-10-23) | **Yes.** A credential proxy injects auth server-side; GitHub uses short-lived GitHub App tokens. ([source](https://docs.guild.ai/platform/credentials.md), checked 2026-10-23) |
| Per-operation credential policies | **No.** Auth is configured per connection; no per-operation policy layer documented. ([source](https://eve.dev/docs/concepts/security-model.md), checked 2026-10-23) | **Yes.** ALLOW/DENY rules by operation, resource, agent, and workspace; DENY wins. ([source](https://docs.guild.ai/platform/credential-policies.md), checked 2026-10-23) |
| Act as the invoking user | **Yes.** Credential owner can be "user"; Vercel Connect supports user-scoped OAuth. ([source](https://eve.dev/docs/connections), checked 2026-10-23) | **Yes.** Member-scoped credentials plus identity mapping for Slack and GitHub users. ([source](https://docs.guild.ai/platform/credentials.md), checked 2026-10-23) |

### Runtime & triggers

| Feature | Vercel eve | Guild |
| --- | --- | --- |
| Managed hosted runtime | **Yes.** Compiles to Vercel Functions with Vercel Workflows for durability. ([source](https://vercel.com/docs/eve), checked 2026-10-23) | **Yes.** Guild hosts and runs all agent types. ([source](https://docs.guild.ai/platform/security-architecture.md), checked 2026-10-23) |
| Self-host option | **Yes.** Run as a Node service or container with your own workflow storage and sandbox. ([source](https://eve.dev/docs/guides/deployment/self-hosting), checked 2026-10-23) | **No.** Hosted only; no self-host option documented. ([source](https://docs.guild.ai/platform/security-architecture.md), checked 2026-10-23) |
| Sandboxed, network-controlled execution | **Partial.** Firecracker microVM sandbox for code execution. ([source](https://vercel.com/docs/eve), checked 2026-10-23) | **Yes.** Containers lose network access before the agent runs; only Guild proxies can reach out. ([source](https://docs.guild.ai/platform/security-architecture.md), checked 2026-10-23) |
| Durable long-running runs | **Yes.** Vercel Workflows event log and replay; survives redeploys. ([source](https://vercel.com/docs/eve), checked 2026-10-23) | **Partial.** Multi-turn sessions; they can be interrupted but not resumed. ([source](https://docs.guild.ai/llms.txt), checked 2026-10-23) |
| Schedules (cron) | **Yes.** defineSchedule({ cron }) or a .md file with cron frontmatter. ([source](https://eve.dev/docs/schedules.md), checked 2026-10-23) | **Partial.** CLI supports --frequency CRON --cron-expression; docs list hourly–monthly presets. ([source](https://docs.guild.ai/platform/triggers.md), checked 2026-10-23) |
| Webhook, event & API triggers | **Yes.** HTTP channel (POST /eve/v1/session) plus GitHub and Linear channels. ([source](https://eve.dev/docs/channels/overview.md), checked 2026-10-23) | **Yes.** Event triggers (Slack mention, GitHub PR, Zendesk ticket, …) and API triggers. ([source](https://docs.guild.ai/platform/triggers.md), checked 2026-10-23) |
| Chat channels (Slack, Teams, …) | **Yes.** Slack, Discord, Teams, Telegram, Twilio, iMessage, GitHub, Linear, and custom channels. ([source](https://eve.dev/docs/channels/overview.md), checked 2026-10-23) | **Yes.** Slack event triggers; Discord, Telegram, and Twilio integrations. ([source](https://docs.guild.ai/integrations/overview.md), checked 2026-10-23) |

### Control & governance

| Feature | Vercel eve | Guild |
| --- | --- | --- |
| Per-tool-call approval gate | **Yes.** approval: always(), once(), auto(), or never() per tool; Jev can auto-approve clear calls. ([source](https://eve.dev/docs/tools.md), checked 2026-10-23) | **Yes.** Approval gates are set in the Guild UI, per agent and per action: when the agent reaches a gated action, the run pauses until a designated human approves. No code needed. ([source](https://www.guild.ai/product/ai-governance), checked 2026-10-23) |
| Roles & access control | **Partial.** Relies on Vercel team roles and Deployment Protection. ([source](https://eve.dev/docs/concepts/security-model.md), checked 2026-10-23) | **Partial.** Admin and Member org roles, restricted workspaces, and scoped API keys. ([source](https://docs.guild.ai/llms.txt), checked 2026-10-23) |
| Audit log | **No.** No eve-specific audit log documented. ([source](https://eve.dev/docs/concepts/security-model.md), checked 2026-10-23) | **Yes.** Immutable, CSV-exportable audit log (admins). ([source](https://docs.guild.ai/llms.txt), checked 2026-10-23) |
| Runtime guardrails & scanning | **Partial.** Jev classifies tool calls as clear or caution before approval. ([source](https://vercel.com/kb/guide/auto-approve-tool-calls-eve-jev), checked 2026-10-23) | **No.** No prompt or tool-call scanning documented; isolation comes from the network-less runtime and credential policies. ([source](https://docs.guild.ai/platform/security-architecture.md), checked 2026-10-23) |
| Spend budgets & usage limits | **Partial.** Vercel Spend Management for the underlying resources. ([source](https://vercel.com/docs/eve/pricing), checked 2026-10-23) | **Yes.** Per-agent and per-workspace spend budgets, model allowlists, and daily token limits. ([source](https://docs.guild.ai/llms.txt), checked 2026-10-23) |
| Multi-provider models with fallbacks | **Yes.** provider/model strings through Vercel AI Gateway. ([source](https://vercel.com/docs/eve/concepts), checked 2026-10-23) | **Yes.** guild.yaml models is an ordered fallback list across Anthropic, OpenAI, Gemini, Meta, DeepSeek, and more; BYO keys supported. ([source](https://docs.guild.ai/guide/guild-yaml.md), checked 2026-10-23) |

### Observability

| Feature | Vercel eve | Guild |
| --- | --- | --- |
| Run traces | **Yes.** Agent Runs in the Vercel dashboard plus OpenTelemetry export. ([source](https://vercel.com/docs/eve/agent-runs), checked 2026-10-23) | **Yes.** Session event log of LLM calls, tool calls, sub-tasks, and container logs; also via the API. ([source](https://docs.guild.ai/llms.txt), checked 2026-10-23) |
| Evaluations | **Yes.** evals/**/*.eval.ts with defineEval and `eve eval`. ([source](https://eve.dev/docs/evals/overview), checked 2026-10-23) | **Partial.** Evaluations with samples, checks, and llmJudge; enabled per account, no CLI command yet. ([source](https://docs.guild.ai/platform/evaluations.md), checked 2026-10-23) |
| Cost & usage tracking | **Yes.** Tokens per run in Agent Runs; billed as Vercel usage. ([source](https://vercel.com/docs/eve/agent-runs), checked 2026-10-23) | **Yes.** Insights and Spend Explorer. ([source](https://docs.guild.ai/llms.txt), checked 2026-10-23) |

### Ecosystem & business

| Feature | Vercel eve | Guild |
| --- | --- | --- |
| Public agent hub (install & fork) | **No.** Registry for channels and extensions; no agent marketplace. ([source](https://eve.dev/integrations), checked 2026-10-23) | **Yes.** Agent Hub: Draft, Internal, or Public; owner~name with semver; install and fork (guild agent init --fork). ([source](https://docs.guild.ai/platform/publish-to-agent-hub.md), checked 2026-10-23) |
| Reusable skills | **Yes.** skills/ directory of Markdown or packaged procedures. ([source](https://eve.dev/docs/reference/agent-files), checked 2026-10-23) | **Yes.** Hub skills, `guild skill`, and skills inside Goose and OpenClaw agents. ([source](https://docs.guild.ai/cli/commands.md), checked 2026-10-23) |
| Full lifecycle CLI | **Yes.** init, dev, build, deploy, eval, add, logs, traces, remote invoke. ([source](https://eve.dev/docs/reference/cli.md), checked 2026-10-23) | **Yes.** 17 top-level commands: init, test, save --publish, workspace chat, trigger, integration, skill, session, and more. ([source](https://docs.guild.ai/cli/commands.md), checked 2026-10-23) |
| Open-source core | **Yes.** Apache-2.0. ([source](https://github.com/vercel/eve), checked 2026-10-23) | **No.** Proprietary platform; the CLI is published on npm. ([source](https://docs.guild.ai/llms.txt), checked 2026-10-23) |
| Public pricing | **Yes.** Framework free; pay for Vercel Functions, Workflows, Sandbox, and AI Gateway usage. ([source](https://vercel.com/docs/eve/pricing), checked 2026-10-23) | **Partial.** No public price list: plans are priced with the Guild team; model usage is metered at list price. ([source](https://docs.guild.ai/reference/pricing.md), checked 2026-10-23) |

## Frequently asked questions

### What is the difference between Guild and Vercel eve?

Vercel eve is an open-source (Apache-2.0) TypeScript framework for long-running agents that deploy to Vercel Functions, Workflows, and Sandbox, or that you host yourself. Guild runs agents for you, built several ways, with no direct network access, secrets kept out of agent code, and a public Agent Hub.

### Can I move an eve agent to Guild without rewriting it?

Mostly, yes: moving an eve agent to Guild is mapping, not rewriting. Tools become entries in agent.ts, connections become Guild integrations, schedules and channels become triggers, and a sandboxed agent becomes an OpenClaw agent. The guild-migrate skill for Claude Code, Codex, or Cursor finds the agent, scaffolds it with the Guild CLI, ports and tests it, and stops before publishing.

### Does Guild support per-tool approvals like eve's approval: always()?

Yes. In Guild you set an approval step in the Guild UI, per agent and per action; when the agent reaches that action, the run pauses until a named person approves. So eve's approval: always() maps to a Guild approval step on the same action, with no code.

### How much does Vercel eve cost compared with Guild?

The eve framework is free; you pay for the Vercel resources it uses, such as Functions, Workflows, Sandbox, and AI Gateway. Guild doesn't publish a price list: plans are priced with the Guild team, and model usage is metered at list price.

### Is Vercel eve production-ready?

Not fully: as of October 2026, Vercel labels eve beta (a public preview announced June 17, 2026), so its APIs may still change. Vercel says it runs more than 100 of its own agents on eve.

### Can I self-host Guild like Vercel eve?

No. As of October 2026, Guild is hosted only. Vercel eve can run as a Node service or container with your own workflow storage and sandbox provider.

## Migrate from Vercel eve to Guild

[The step-by-step migration guide](https://docs.guild.ai/migrations/vercel-eve): what to take stock of, how each piece maps, and what doesn’t map one to one.

## Sources

- [vercel.com/docs/eve/concepts](https://vercel.com/docs/eve/concepts)
- [vercel.com/docs/eve](https://vercel.com/docs/eve)
- [eve.dev/docs/reference/agent-files](https://eve.dev/docs/reference/agent-files)
- [eve.dev/docs/tools](https://eve.dev/docs/tools.md)
- [eve.dev/integrations](https://eve.dev/integrations)
- [eve.dev/docs/connections](https://eve.dev/docs/connections)
- [eve.dev/docs/channels/overview](https://eve.dev/docs/channels/overview.md)
- [eve.dev/docs/concepts/security-model](https://eve.dev/docs/concepts/security-model.md)
- [eve.dev/docs/guides/deployment/self-hosting](https://eve.dev/docs/guides/deployment/self-hosting)
- [eve.dev/docs/schedules](https://eve.dev/docs/schedules.md)
- [vercel.com/kb/guide/auto-approve-tool-calls-eve-jev](https://vercel.com/kb/guide/auto-approve-tool-calls-eve-jev)
- [vercel.com/docs/eve/pricing](https://vercel.com/docs/eve/pricing)
- [vercel.com/docs/eve/agent-runs](https://vercel.com/docs/eve/agent-runs)
- [eve.dev/docs/evals/overview](https://eve.dev/docs/evals/overview)
- [eve.dev/docs/reference/cli](https://eve.dev/docs/reference/cli.md)
- [github.com/vercel/eve](https://github.com/vercel/eve)
- [docs.guild.ai/packages/agents-sdk](https://docs.guild.ai/packages/agents-sdk.md)
- [docs.guild.ai/guide/agent-types](https://docs.guild.ai/guide/agent-types.md)
- [docs.guild.ai/guide/guild-yaml](https://docs.guild.ai/guide/guild-yaml.md)
- [docs.guild.ai/integrations/overview](https://docs.guild.ai/integrations/overview.md)
- [docs.guild.ai/api-reference/mcp](https://docs.guild.ai/api-reference/mcp.md)
- [docs.guild.ai/platform/credentials](https://docs.guild.ai/platform/credentials.md)
- [docs.guild.ai/platform/credential-policies](https://docs.guild.ai/platform/credential-policies.md)
- [docs.guild.ai/platform/security-architecture](https://docs.guild.ai/platform/security-architecture.md)
- [docs.guild.ai/llms.txt](https://docs.guild.ai/llms.txt)
- [docs.guild.ai/platform/triggers](https://docs.guild.ai/platform/triggers.md)
- [guild.ai/product/ai-governance](https://www.guild.ai/product/ai-governance)
- [docs.guild.ai/platform/evaluations](https://docs.guild.ai/platform/evaluations.md)
- [docs.guild.ai/platform/publish-to-agent-hub](https://docs.guild.ai/platform/publish-to-agent-hub.md)
- [docs.guild.ai/cli/commands](https://docs.guild.ai/cli/commands.md)
- [docs.guild.ai/reference/pricing](https://docs.guild.ai/reference/pricing.md)

## Other comparisons

- [Guild vs. Claude Managed Agents](https://www.guild.ai/compare/claude-managed-agents)
- [Guild vs. AWS](https://www.guild.ai/compare/aws)
- [Guild vs. LangChain](https://www.guild.ai/compare/langchain)
- [Guild vs. Runlayer](https://www.guild.ai/compare/runlayer)
- [Guild vs. Arcade](https://www.guild.ai/compare/arcade)
- [All comparisons](https://www.guild.ai/compare)
- [Book a demo](https://www.guild.ai/talk-to-sales)