---
title: "Guild vs Arcade"
description: "Guild vs Arcade: per-user tools, MCP gateways, and tool evals compared with Guild's agents, triggers, permissions, and Agent Hub, plus how to move Arcade-backed agents."
canonical: "https://www.guild.ai/compare/arcade"
---

# Guild vs Arcade

Guild vs Arcade: per-user tools, MCP gateways, and tool evals compared with Guild's agents, triggers, permissions, and Agent Hub, plus how to move Arcade-backed agents.

Arcade gives agents you build elsewhere tools that act with each user's own accounts, from about 126 integrations. It doesn't run agents. Guild does: it runs and triggers them, keeps secrets out of agent code, and shares them on a public Agent Hub. The two can work together.

Last verified 2026-10-30. Across 35 features, Guild leads on 23, Arcade on 5, and 7 are level. Every cell below names its source.

## When to choose Arcade

- You ship an app where each of your customers' users signs in to tools with their own accounts.
- You need a big catalog of agent-ready tools now and want to keep your agent framework.
- You must self-host the tool layer in a VPC or an air-gapped environment.
- You want to test how well different models pick tools and fill in their inputs.
- You want hooks that can change or redact what goes into and out of a tool.

## When to choose Guild

- You need somewhere to run the agents themselves, with schedules, events, and API triggers.
- Your team builds agents more than one way, including repo agents with shell and git, Goose recipes, or Python LangGraph.
- You want to share, version, and reuse agents on a public Agent Hub.
- You want each agent to get only the access it needs, down to single actions.
- You want one CLI for agents, integrations, triggers, and workspace chat.

## What Arcade and Guild are

**Arcade.** Arcade sits between agents and business systems. It runs the sign-in for each user and service, keeps tokens in an encrypted vault, and runs tools from its catalog or your own MCP servers. Its gateways serve tools to Claude, Cursor, ChatGPT, and others, and hooks can block, change, or redact calls. Self-hosting is Enterprise only.

**Guild.** Guild is where the agent lives: built several ways, tested and versioned from one CLI, started by schedules, events, or API calls, and shared on the Agent Hub. Integrations go through Guild, so secrets stay out of agent code, you decide which actions each agent can take, and agents can't reach the network directly.

|   | Arcade | Guild |
| --- | --- | --- |
| Category | AI actions runtime and tool-calling platform | One platform to run and control AI agents |
| License | MIT framework and SDKs (arcade-js Apache-2.0); Engine closed source (inferred) | Proprietary platform; CLI published on npm as @guildai/cli |
| Pricing | Free $0 (2k auth events + 2k tool calls/month), Team $25/month + usage, Enterprise custom | No public price list; plans priced with the Guild team; model usage metered at list price |
| Maturity | Generally available (arcade-mcp 1.16.3, 2026-10-14) | Generally available |
| Docs | https://docs.arcade.dev | https://docs.guild.ai |

## Concept map: Arcade to Guild

| Concept | Arcade | Guild | Note |
| --- | --- | --- | --- |
| Custom tools | An `MCPApp` server with `@app.tool` (`arcade-mcp`) | A custom Guild integration from the MCP server or an OpenAPI spec (`guild integration create`, Porter) | Or keep the server and register it as a remote MCP integration; verify on your account. |
| Prebuilt toolkits | Optimized toolkits (Gmail, Slack, GitHub, Linear, Notion, …) | Guild native integrations (`guildai~github`, `guildai~slack`, …) | Check operation names with `guild integration operation list <owner~name> --json`. |
| User auth | `requires_auth=GitHub()` and auth providers | An integration connection + member-scoped credentials, with Slack and GitHub identity mapping |   |
| Secrets | `requires_secrets` / `context.get_secret()` | Credentials (account, workspace, member, or agent scope), or workspace variables (`task.env`) |   |
| Calling tools | `client.tools.execute` / `client.tools.authorize` in agent code | Tools declared on the agent (`guildServiceTool` / `@guildai-services/*` in TypeScript, `guild.yaml` integrations elsewhere); `guild_credentials_request` asks the user to connect |   |
| End users | `user_id` per end user | Guild members + identity mapping; member-scoped credentials | Per-end-user OAuth for customers of an app you ship has no 1:1 equivalent. |
| MCP gateway | MCP Gateway (`api.arcade.dev/mcp/{slug}`) | Integrations declared per agent | Guild's MCP server (`api.guild.ai/mcp`) exposes Guild itself, not an aggregated tool gateway. |
| Access hooks | Contextual Access pre/post-execution hooks | Credential policies (ALLOW/DENY by operation, resource, agent, workspace) | No modify or redact equivalent. |
| Tool evals | `arcade evals` (`EvalSuite`, critics) | `guild agent test` and Guild Evaluations (`hasToolCall`, `toolCallContains`, `llmJudge`) |   |
| Hosting | `arcade deploy` (MCP server to Arcade Cloud) | `guild integration version create / build / publish` for tools; `guild agent save --wait --publish` for agents |   |
| Agent framework | Your agent framework (LangChain, OpenAI Agents, Mastra, …) | A Guild agent: TypeScript, Native, OpenClaw, Goose, or LangGraph |   |
| Observability | Execution records, audit logs, OpenTelemetry | Sessions and the session event log, audit log, Insights and Spend Explorer |   |

## Feature by feature: Arcade vs. Guild

### Authoring

| Feature | Arcade | Guild |
| --- | --- | --- |
| Code-first TypeScript agents | **No.** Arcade provides tools for agents you build elsewhere. The TypeScript client @arcadeai/arcadejs calls Arcade tools from Vercel AI SDK, Mastra, or LangChain JS agents; the TypeScript server framework (arcade-mcp-ts) is archived. ([source](https://docs.arcade.dev/en/get-started/quickstarts/call-tool-agent), 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.** No agent hosting. Your own LangGraph agent calls Arcade tools through arcadepy; langchain-arcade is deprecated. ([source](https://docs.arcade.dev/en/get-started/agent-frameworks), 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 | **No.** No agent builder. The dashboard configures tools, MCP gateways, and auth, not agents. ([source](https://docs.arcade.dev/en/build), 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.** Framework-neutral for tools (LangChain, OpenAI Agents, CrewAI, Google ADK, Mastra, Vercel AI SDK, Spring AI), but Arcade does not run agents itself. ([source](https://docs.arcade.dev/en/get-started/agent-frameworks), 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.** Tools are typed with Python type hints and Annotated descriptions. There are no agents to type. ([source](https://docs.arcade.dev/en/references/mcp/python), 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) | **No.** No agent runtime or agent sandbox. Arcade provides tools for agents you build elsewhere. ([source](https://docs.arcade.dev/en/build), 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 | **No.** No agents to delegate between; orchestration lives in your own framework. ([source](https://docs.arcade.dev/en/build), 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 | Arcade | Guild |
| --- | --- | --- |
| Managed integrations catalog | **Yes.** 126 integrations as of 2026-10-23 (84 Optimized, 40 Starter API wrappers, 2 Partner), marketed as 8,000+ tools. ([source](https://docs.arcade.dev/en/resources/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.** Register any Streamable-HTTP MCP server as a remote server; Arcade runs per-user OAuth for it. Tools only (no prompts, resources, or sampling). ([source](https://docs.arcade.dev/en/operate/governance/remote-mcp-servers), 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 Gateways at api.arcade.dev/mcp/{slug} combine tools from many servers for Claude, Cursor, VS Code, ChatGPT, Codex, and other clients. ([source](https://docs.arcade.dev/en/operate/governance/mcp-gateways), 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 | **No.** No OpenAPI import documented. Custom tools are written in Python with arcade-mcp, or brought in as remote MCP servers. ([source](https://docs.arcade.dev/en/build/create-tools/tool-basics/build-mcp-server), 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.** End-user tokens and tool secrets are stored encrypted in the Engine's token vault; the LLM and client never see token values. ([source](https://docs.arcade.dev/en/operate/deploy/architecture), 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 | **Partial.** Contextual Access pre- and post-execution webhooks can allow, deny, modify, or redact each tool call, plus group-based access and rate limits. The policy is a webhook you host, not declarative per-operation rules. ([source](https://docs.arcade.dev/en/operate/governance/contextual-access), 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.** Arcade's core feature: per-user OAuth keyed by user_id across 33 auth providers plus generic OAuth 2.0, with IdP User Sources and a custom user verifier for production. ([source](https://docs.arcade.dev/en/references/auth-providers), 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 | Arcade | Guild |
| --- | --- | --- |
| Managed hosted runtime | **Partial.** Arcade Cloud hosts tools and your MCP servers (arcade deploy), not agents. ([source](https://docs.arcade.dev/en/build/arcade-deploy), 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.** Helm chart on Kubernetes 1.30+, VPC, air-gapped, or hybrid, plus Azure and AWS marketplace offers. In practice self-hosting is on the Enterprise tier. ([source](https://docs.arcade.dev/en/operate/deploy), 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.** Tool code runs in separate worker runtimes (arcadedev/worker) or your own MCP servers. No agent sandbox or network-egress policy is documented. ([source](https://docs.arcade.dev/en/operate/deploy/worker), 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 | **No.** Tool calls are request and response; there are no durable agent runs. ([source](https://docs.arcade.dev/en/build), 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) | **No.** No schedules or triggers documented. Scheduling belongs to the agent framework you bring. ([source](https://docs.arcade.dev/en/build), 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 | **Partial.** Tools can be executed over the REST API (client.tools.execute), but nothing triggers agents: there are no event or webhook triggers. ([source](https://docs.arcade.dev/en/get-started/quickstarts/call-tool-agent), 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, …) | **No.** No chat channels. Slack and Microsoft Teams are tool integrations, not entry points to agents. ([source](https://docs.arcade.dev/en/resources/integrations), 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 | Arcade | Guild |
| --- | --- | --- |
| Per-tool-call approval gate | **Partial.** No native approval queue. Pre-execution hooks can deny or modify a call and per-user OAuth consent gates first use; human approval lives in your agent (for example a LangGraph interrupt). ([source](https://docs.arcade.dev/en/operate/governance/contextual-access), 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 | **Yes.** Orgs, projects, and roles, with RBAC through OpenFGA; SSO and RBAC are listed on the Enterprise tier. ([source](https://docs.arcade.dev/en/operate/deploy/architecture), 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 | **Yes.** Audit logs of admin actions through a REST API at org or project scope, plus per-tool execution records. SIEM streaming is claimed on the homepage but not shown in the docs. ([source](https://docs.arcade.dev/en/operate/governance/audit-logs), 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.** Contextual Access hooks can deny, modify, or redact tool inputs and outputs; the inspection logic is yours to host. No built-in PII or prompt-injection scanner is documented. ([source](https://docs.arcade.dev/en/operate/governance/contextual-access), 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.** Rate limits through Contextual Access; usage is metered as auth events and tool calls. No per-agent token or spend budgets. ([source](https://docs.arcade.dev/en/operate/governance/contextual-access), 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 | **No.** Arcade does not route LLM calls. Tool Recommendation narrows the tool list to cut token use. ([source](https://www.arcade.dev/), 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 | Arcade | Guild |
| --- | --- | --- |
| Run traces | **Partial.** Tool-execution records in the dashboard and OpenTelemetry from the framework and Helm chart. No agent-level traces. ([source](https://docs.arcade.dev/en/operate/deploy/architecture), 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 | **Partial.** arcade evals scores tool selection and argument accuracy (EvalSuite, critics, comparative runs). It does not evaluate end-to-end agent behavior. ([source](https://docs.arcade.dev/en/build/create-tools/evaluate-tools/create-evaluation-suite), 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 | **Partial.** Usage is metered as auth events and tool calls. LLM costs are not tracked. ([source](https://www.arcade.dev/pricing), checked 2026-10-23) | **Yes.** Insights and Spend Explorer. ([source](https://docs.guild.ai/llms.txt), checked 2026-10-23) |

### Ecosystem & business

| Feature | Arcade | Guild |
| --- | --- | --- |
| Public agent hub (install & fork) | **No.** No agent hub. The integrations catalog and Enterprise private registry cover tools, not agents. ([source](https://docs.arcade.dev/en/resources/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 | **No.** No reusable skills format. The MIT arcade-plugin connects coding clients to Arcade's hosted gateway. ([source](https://docs.arcade.dev/en/get-started/agent-plugin), 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 | **Partial.** The arcade CLI covers tool servers end to end (new, mcp, deploy, evals, secret, server logs, configure). It has no agent commands. ([source](https://docs.arcade.dev/en/references/arcade-cli), 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 | **Partial.** The arcade-mcp framework and arcadepy are MIT and arcade-js is Apache-2.0. The Engine, Coordinator, and Dashboard ship as images and a Helm chart (closed source, inferred). ([source](https://github.com/ArcadeAI/arcade-mcp), 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.** Free $0 (2,000 auth events and 2,000 tool calls a month); Team $25/month plus $0.10 per auth event and $0.01 per tool call; Enterprise custom. ([source](https://www.arcade.dev/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 Arcade?

Arcade gives agents built with other frameworks tools that act with each user's own accounts: about 126 integrations, MCP gateways, policy hooks, and tool evals. Guild is the agent platform itself: it builds, runs, triggers, and shares agents, with integrations that keep secrets out of agent code and permissions per action.

### Is Arcade an agent platform?

No. Arcade provides authorized tools for agents you build with another framework, such as LangChain, OpenAI Agents, CrewAI, Google ADK, Mastra, or the Vercel AI SDK. As of October 2026, it has no agent builder, hosted agents, triggers, or agent hub.

### Can I use Arcade and Guild together?

Likely, yes: keep Arcade for tools and run the agents on Guild by adding your Arcade MCP Gateway or arcade-mcp server as a custom Guild integration. Check that MCP-based custom integrations work on your Guild account before you rely on it.

### How do I move an Arcade-backed agent to Guild?

Move the agent logic into a Guild agent, then swap each Arcade toolkit for the matching Guild integration. Arcade requires\_auth providers become integration connections with member-scoped credentials, requires\_secrets become credentials, and arcade evals suites become Guild Evaluations or guild agent test cases. The guild-migrate skill finds arcade-mcp, arcadepy, and @arcadeai/arcadejs usage and maps each Arcade tool to a Guild integration.

### What can Arcade do that Guild can't?

Three things, as of October 2026: sign-in with each end user's own accounts for an app you ship to customers, hooks that change or redact tool calls, and self-hosting. Guild maps users to workspace members, its policies allow or block calls but don't rewrite them, and it's hosted only.

### How much does Arcade cost?

As of October 2026, Arcade's Free plan is $0 with 2,000 auth events and 2,000 tool calls a month; Team is $25 a month plus $0.10 per auth event and $0.01 per tool call; Enterprise is custom. Guild doesn't publish a price list: plans are priced with the Guild team, and model usage is metered at list price.

## Migrate from Arcade to Guild

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

## Sources

- [docs.arcade.dev/en/get-started/quickstarts/call-tool-agent](https://docs.arcade.dev/en/get-started/quickstarts/call-tool-agent)
- [docs.arcade.dev/en/get-started/agent-frameworks](https://docs.arcade.dev/en/get-started/agent-frameworks)
- [docs.arcade.dev/en/build](https://docs.arcade.dev/en/build)
- [docs.arcade.dev/en/references/mcp/python](https://docs.arcade.dev/en/references/mcp/python)
- [docs.arcade.dev/en/resources/integrations](https://docs.arcade.dev/en/resources/integrations)
- [docs.arcade.dev/en/operate/governance/remote-mcp-servers](https://docs.arcade.dev/en/operate/governance/remote-mcp-servers)
- [docs.arcade.dev/en/operate/governance/mcp-gateways](https://docs.arcade.dev/en/operate/governance/mcp-gateways)
- [docs.arcade.dev/en/build/create-tools/tool-basics/build-mcp-server](https://docs.arcade.dev/en/build/create-tools/tool-basics/build-mcp-server)
- [docs.arcade.dev/en/operate/deploy/architecture](https://docs.arcade.dev/en/operate/deploy/architecture)
- [docs.arcade.dev/en/operate/governance/contextual-access](https://docs.arcade.dev/en/operate/governance/contextual-access)
- [docs.arcade.dev/en/references/auth-providers](https://docs.arcade.dev/en/references/auth-providers)
- [docs.arcade.dev/en/build/arcade-deploy](https://docs.arcade.dev/en/build/arcade-deploy)
- [docs.arcade.dev/en/operate/deploy](https://docs.arcade.dev/en/operate/deploy)
- [docs.arcade.dev/en/operate/deploy/worker](https://docs.arcade.dev/en/operate/deploy/worker)
- [docs.arcade.dev/en/operate/governance/audit-logs](https://docs.arcade.dev/en/operate/governance/audit-logs)
- [arcade.dev](https://www.arcade.dev/)
- [docs.arcade.dev/en/build/create-tools/evaluate-tools/create-evaluation-suite](https://docs.arcade.dev/en/build/create-tools/evaluate-tools/create-evaluation-suite)
- [arcade.dev/pricing](https://www.arcade.dev/pricing)
- [docs.arcade.dev/en/get-started/agent-plugin](https://docs.arcade.dev/en/get-started/agent-plugin)
- [docs.arcade.dev/en/references/arcade-cli](https://docs.arcade.dev/en/references/arcade-cli)
- [github.com/ArcadeAI/arcade-mcp](https://github.com/ArcadeAI/arcade-mcp)
- [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. Vercel eve](https://www.guild.ai/compare/vercel-eve)
- [All comparisons](https://www.guild.ai/compare)
- [Book a demo](https://www.guild.ai/talk-to-sales)