---
title: "Guild vs AWS (Amazon Bedrock AgentCore)"
description: "Guild vs Amazon Bedrock AgentCore: runtime, tools, identity, policy, and evaluations compared with Guild's agents, permissions, triggers, Agent Hub, and CLI."
canonical: "https://www.guild.ai/compare/aws"
---

# Guild vs AWS (Amazon Bedrock AgentCore)

Guild vs Amazon Bedrock AgentCore: runtime, tools, identity, policy, and evaluations compared with Guild's agents, permissions, triggers, Agent Hub, and CLI.

Amazon Bedrock AgentCore is a set of AWS services you put together into an agent platform. Guild is one product with those pieces already connected: it runs your agents, keeps secrets out of agent code, and adds triggers, approvals, and a public Agent Hub.

Last verified 2026-10-30. Across 35 features, Guild leads on 7, AWS on 6, and 22 are level. Every cell below names its source.

## When to choose AWS

- Your company runs on AWS and wants agents under IAM, CloudTrail, and your AWS bill.
- Agents must run inside your VPC and reach private databases and services.
- You want single services, like Gateway or Identity, for agents you host elsewhere.
- You need sessions longer than a few hours, built-in browser and code tools, or GovCloud.
- You want Bedrock Guardrails to screen every tool call for prompt injection and personal data.

## When to choose Guild

- You want one product with triggers, approvals, budgets, and audit already connected.
- You want agents to start from a schedule, Slack, or GitHub without wiring EventBridge, API Gateway, and Lambda.
- You want approval steps set in a UI, per agent and per action, with no code.
- You want spend limits per agent and per workspace, not only per-call token caps.
- You want to share, version, and reuse agents on a public Agent Hub.
- You use models from several providers, with Bedrock as one option.

## What AWS and Guild are

**AWS.** AgentCore gives AWS teams the building blocks: a runtime for any framework, a Gateway that turns APIs into tools, Identity for logins and keys, and Policy with Bedrock Guardrails. It all runs in your AWS account, under IAM and inside your VPC if you want. Schedules and chat apps are other AWS services you wire up yourself.

**Guild.** Guild ships those pieces already connected. Agents can't reach the network directly, secrets stay out of agent code, and you decide which actions each agent can take. Triggers, approvals, spend limits, audit, and the Agent Hub are built in, so you set rules instead of building infrastructure.

|   | AWS | Guild |
| --- | --- | --- |
| Category | Managed cloud agent services | One platform to run and control AI agents |
| License | Proprietary AWS services; Strands Agents SDKs, AgentCore CLI, and AgentCore Python SDK are Apache-2.0 | Proprietary platform; CLI published on npm as @guildai/cli |
| Pricing | Consumption-based per service, no minimums; e.g. Runtime from $0.0895 per vCPU-hour; no separate Harness charge | No public price list; plans priced with the Guild team; model usage metered at list price |
| Maturity | Generally available (October 2025); Harness GA July 2026 | Generally available |
| Docs | https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/ | https://docs.guild.ai |

## Concept map: AWS to Guild

| Concept | AWS | Guild | Note |
| --- | --- | --- | --- |
| Instruction-only agent | AgentCore Harness: `CreateHarness` with model, system prompt, tools, and skills | Native agent: `PROMPT.md` + `guild.yaml` |   |
| Code agent | Strands, LangGraph, or other framework code behind a `BedrockAgentCoreApp` entrypoint on Runtime | TypeScript `agent()` or `llmAgent()`, or the LangGraph agent type (`langgraph.json` + `graph.py`) |   |
| Agent with shell and files | Harness session microVM with shell and filesystem, or a custom container | The OpenClaw agent type: `AGENTS.md` + `skills/`, with shell, git, and files |   |
| Tools from APIs | Gateway targets: OpenAPI, Smithy, Lambda, MCP servers, provider templates | Guild integrations built with `guild integration` from OpenAPI specs or MCP servers |   |
| Credentials | Identity token vault and credential providers, scoped with IAM | Credentials scoped to an account, workspace, member, or agent | Guild keeps secrets in the credential proxy for every agent type. |
| Acting as the user | 3-legged OAuth and on-behalf-of token exchange | Member-scoped credentials plus identity mapping for Slack and GitHub users |   |
| Rules on tool calls | Policy in AgentCore: Cedar or Dogwood permit/forbid on Gateway tool calls | ALLOW/DENY credential policies by operation, resource, agent, and workspace |   |
| Human approval | Strands interrupts in a `BeforeToolCallEvent` hook | An approval gate on the same action, set in the Guild UI | Per agent and per action; no code needed. |
| Sub-agents | Strands agents-as-tools, swarm, graph, or A2A | `guildAgentTool({ calls: 'owner~agent' })`, or `sub_agents` in `guild.yaml` |   |
| Skills | Harness skills from the AWS catalog, Git, or S3 | Hub skills and `guild skill`, or OpenClaw `skills/<name>/SKILL.md` |   |
| Schedules | Amazon EventBridge calling the Runtime endpoint | A schedule trigger: `guild trigger create --type time` |   |
| Models | Harness model config; Gateway rules for fallback | `models` in `guild.yaml`: an ordered fallback list across providers | Guild can route Claude, GPT, and other models through Bedrock in your AWS account by assuming an IAM role. |
| Limits | Harness `maxTokens` and `maxIterations`; Gateway rate limits | Per-agent and per-workspace spend budgets, daily token limits, model allowlists |   |
| Access and audit | IAM policies and CloudTrail | Admin and Member roles, restricted workspaces, scoped API keys, and the audit log |   |
| Agent catalog | AWS Agent Registry (private) and AWS Marketplace | Agent Hub: Draft, Internal, or Public, with install and fork |   |
| Tracing | AgentCore Observability in CloudWatch | Sessions and the session event log |   |
| Evals | AgentCore Evaluations | Guild Evaluations and `guild agent test` |   |
| Deploy | `agentcore deploy` | `guild agent save --wait --publish` |   |

## Feature by feature: AWS vs. Guild

### Authoring

| Feature | AWS | Guild |
| --- | --- | --- |
| Code-first TypeScript agents | **Yes.** Strands Agents TypeScript SDK (@strands-agents/sdk), deployable to AgentCore Runtime. ([source](https://strandsagents.com/docs/user-guide/sdk/quickstart/typescript/index.md), checked 2026-10-30) | **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 | **Yes.** AgentCore Runtime hosts LangGraph agents (and other Python frameworks) wrapped in the BedrockAgentCoreApp entrypoint. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.html), checked 2026-10-30) | **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 | **Yes.** AgentCore Harness (GA July 2026): CreateHarness takes model, system prompt, tools, and skills as configuration; no orchestration code or container. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness.html), checked 2026-10-30) | **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 | **Yes.** AgentCore Runtime runs Strands, LangGraph, CrewAI, LlamaIndex, Google ADK, OpenAI Agents SDK, or custom code, next to config-only Harness agents. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.html), checked 2026-10-30) | **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.** Strands structured output returns typed results in code; AgentCore Runtime invocations take a free-form payload with no declared agent schema. ([source](https://strandsagents.com/docs/user-guide/sdk/agents/structured-output/index.md), checked 2026-10-30) | **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.** AgentCore Harness gives each session its own microVM with a filesystem, shell, and file tools; bring your own container image. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness.html), checked 2026-10-30) | **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.** Strands agents-as-tools, swarm, graph, and A2A; AgentCore Runtime hosts A2A servers. Harness itself does not do graph or multi-agent patterns. ([source](https://strandsagents.com/docs/user-guide/sdk/multi-agent/multi-agent-patterns/index.md), checked 2026-10-30) | **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 | AWS | Guild |
| --- | --- | --- |
| Managed integrations catalog | **Partial.** AgentCore Gateway has 16 provider templates (Slack, Jira, Salesforce, ServiceNow, Zendesk, Microsoft, …) that each expose a subset of the provider's API, plus Web Search and Step Functions connectors. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway-target-integrations.html), checked 2026-10-30) | **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.** AgentCore Gateway takes MCP servers as targets; Harness and Strands connect to remote MCP servers directly. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway-target-MCPservers.html), checked 2026-10-30) | **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.** Gateway serves tools as an MCP endpoint, Runtime hosts MCP servers, and the AgentCore MCP Server lets coding assistants deploy and invoke agents. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/mcp-getting-started.html), checked 2026-10-30) | **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.** AgentCore Gateway turns OpenAPI schemas, Smithy models, Lambda functions, and API Gateway stages into MCP tools. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway-schema-openapi.html), checked 2026-10-30) | **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 | **Partial.** AgentCore Gateway injects OAuth and API key credentials from the Identity token vault on outbound calls; code on Runtime that uses @requires_access_token receives the token itself. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/key-features-and-benefits.html), checked 2026-10-30) | **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 | **Yes.** Policy in AgentCore: Cedar or Dogwood permit/forbid rules on every Gateway tool call, by principal, tool, and input values; default-deny, forbid wins. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/policy-core-concepts.html), checked 2026-10-30) | **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.** AgentCore Identity and Gateway support 3-legged OAuth and on-behalf-of token exchange carrying both the user's and the agent's identity. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway-outbound-auth.html), checked 2026-10-30) | **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 | AWS | Guild |
| --- | --- | --- |
| Managed hosted runtime | **Yes.** AgentCore Runtime is serverless and runs each session in its own microVM; Harness runs on top of it. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness-vs-runtime.html), checked 2026-10-30) | **Yes.** Guild hosts and runs all agent types. ([source](https://docs.guild.ai/platform/security-architecture.md), checked 2026-10-23) |
| Self-host option | **Partial.** AgentCore is AWS-managed only. Runtime Instances run on AWS-managed EC2 in your own AWS account; Strands agents can run anywhere without AgentCore. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-instances.html), checked 2026-10-30) | **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 | **Yes.** One microVM per session; in VPC mode, Runtime, Code Interpreter, and Browser have no internet access unless you add a NAT gateway, and security groups control egress. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/agentcore-vpc.html), checked 2026-10-30) | **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 | **Partial.** AgentCore Runtime sessions last up to 8 hours on microVMs (14 days on Instances) and resume on a new microVM with persisted storage; no checkpoint-and-replay of the agent loop. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-lifecycle-settings.html), checked 2026-10-30) | **Partial.** Multi-turn sessions; they can be interrupted but not resumed. ([source](https://docs.guild.ai/llms.txt), checked 2026-10-23) |
| Schedules (cron) | **Via integration.** No AgentCore scheduler; an Amazon EventBridge rule or schedule calls the Runtime endpoint. ([source](https://aws.amazon.com/blogs/storage/orchestrating-multi-agent-ai-architectures-with-amazon-s3-files/), checked 2026-10-30) | **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.** InvokeAgentRuntime and InvokeHarness APIs with IAM or OAuth auth over HTTP, MCP, A2A, AG-UI, or WebSocket; Step Functions has an InvokeHarness state. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-invoke-agent.html), checked 2026-10-30) | **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, …) | **Via integration.** No built-in channels; an AWS sample wires Slack to AgentCore Runtime with API Gateway, Lambda, and SQS. No Teams path documented. ([source](https://aws.amazon.com/blogs/machine-learning/integrating-amazon-bedrock-agentcore-with-slack/), checked 2026-10-30) | **Yes.** Slack event triggers; Discord, Telegram, and Twilio integrations. ([source](https://docs.guild.ai/integrations/overview.md), checked 2026-10-23) |

### Control & governance

| Feature | AWS | Guild |
| --- | --- | --- |
| Per-tool-call approval gate | **Yes.** Strands interrupts in a BeforeToolCallEvent hook pause a tool call until your app returns an approval; written in code. Policy temporal rules can require a prior approval action. ([source](https://strandsagents.com/docs/user-guide/sdk/interrupts/index.md), checked 2026-10-30) | **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.** AWS IAM identity and resource-based policies, with AgentCore condition keys, control who can create, invoke, and read each resource. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/security_iam_service-with-iam.html), checked 2026-10-30) | **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.** AWS CloudTrail records AgentCore management and data events, including every harness and runtime invocation. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness-operations.html), checked 2026-10-30) | **Yes.** Immutable, CSV-exportable audit log (admins). ([source](https://docs.guild.ai/llms.txt), checked 2026-10-23) |
| Runtime guardrails & scanning | **Yes.** Amazon Bedrock Guardrails inside AgentCore Policy screen Gateway traffic for prompt injection, jailbreaks, PII, and harmful content. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/policy-guardrails-getting-started.html), checked 2026-10-30) | **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.** Harness caps maxTokens, maxIterations, and time per invocation; Gateway rate limits cap tokens per minute by caller or model. No per-agent dollar budget in AgentCore. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness-operations.html), checked 2026-10-30) | **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.** Harness uses Bedrock, OpenAI, Gemini, or any LiteLLM-compatible provider and can switch mid-session; Gateway rules add ordered model fallback chains. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/release-notes.html), checked 2026-10-30) | **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 | AWS | Guild |
| --- | --- | --- |
| Run traces | **Yes.** AgentCore Observability: OpenTelemetry traces of model calls, tool calls, and memory operations in Amazon CloudWatch. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness-operations.html), checked 2026-10-30) | **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.** AgentCore Evaluations (GA March 2026): built-in and custom evaluators, online, on-demand, and batch runs, plus A/B tests. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/evaluations.html), checked 2026-10-30) | **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.** Token usage in invocation metadata and traces; billed cost via AWS Cost Explorer with harness tags as cost allocation tags. AWS says observability is not a billing report. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness-operations.html), checked 2026-10-30) | **Yes.** Insights and Spend Explorer. ([source](https://docs.guild.ai/llms.txt), checked 2026-10-23) |

### Ecosystem & business

| Feature | AWS | Guild |
| --- | --- | --- |
| Public agent hub (install & fork) | **Partial.** AWS Marketplace lists third-party agents and tools you buy and deploy to AgentCore; AWS Agent Registry is a private catalog. No public install-and-fork hub. ([source](https://aws.amazon.com/about-aws/whats-new/2025/07/ai-agents-tools-aws-marketplace/), checked 2026-10-30) | **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.** Harness loads SKILL.md skills from the AWS skills catalog, Git, Amazon S3, or the session filesystem; Registry catalogs skills. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness-skills.html), checked 2026-10-30) | **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.** AgentCore CLI v1 (@aws/agentcore): create, add, dev, deploy, invoke, logs, traces, eval, plus harness, runtime, gateway, and memory commands. ([source](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/release-notes.html), checked 2026-10-30) | **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.** Strands Agents, the AgentCore CLI, and the AgentCore Python SDK are Apache-2.0; the AgentCore services themselves are proprietary. ([source](https://github.com/aws/agentcore-cli), checked 2026-10-30) | **No.** Proprietary platform; the CLI is published on npm. ([source](https://docs.guild.ai/llms.txt), checked 2026-10-23) |
| Public pricing | **Yes.** Per-service rates published (e.g. Runtime $0.0895 per vCPU-hour, Gateway $0.005 per 1,000 invocations); no separate Harness charge. ([source](https://aws.amazon.com/bedrock/agentcore/pricing/), checked 2026-10-30) | **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

### Is Guild an alternative to Amazon Bedrock AgentCore?

Yes, for teams that want to build, run, and control agents without assembling AWS services. AgentCore is a set of separate services: Runtime, Harness, Gateway, Identity, Policy, Memory, Observability, and Evaluations. Guild is one hosted product that runs agents built several ways, with secrets kept out of agent code, permissions per action, triggers, approvals, spend limits, audit, and a public Agent Hub. Teams all-in on AWS may still prefer AgentCore.

### Can Guild run in my AWS account?

Not the platform itself. As of October 2026, Guild is hosted only, while AgentCore runs in your AWS account and can use your VPC. Guild can call models on Amazon Bedrock in your account: you create an IAM role for Guild to use, Guild never stores long-lived AWS keys, and AWS bills the model calls to you.

### What is the difference between AgentCore Runtime and AgentCore Harness?

AgentCore Runtime hosts agent code you write in any framework, with one microVM per session. AgentCore Harness, generally available since July 2026, runs an agent you describe as configuration (model, prompt, tools, and skills) on Strands Agents. In Guild, the closest match to Harness is a Native agent.

### How do AgentCore Policy and Guild credential policies compare?

AgentCore Policy checks Cedar or Dogwood rules on every tool call through AgentCore Gateway, by who is calling, which tool, and its inputs, and can add Bedrock Guardrails checks. Guild's credential policies allow or block each action by operation, resource, agent, and workspace, and every Guild agent goes through them. In both, a matching deny rule wins.

### Does Amazon Bedrock AgentCore have schedules and Slack triggers?

Not built in. As of October 2026, AgentCore has no scheduler or chat apps: AWS shows EventBridge calling the runtime for schedules, and a sample that connects Slack through API Gateway, Lambda, and SQS. Guild starts agents from schedules, Slack mentions, GitHub pull requests, Zendesk tickets, and more.

### How much does Amazon Bedrock AgentCore cost compared with Guild?

AgentCore charges per service with no minimums. As of October 2026, Runtime starts at $0.0895 per vCPU-hour, Gateway costs $0.005 per 1,000 calls, and Harness has no separate charge; models and CloudWatch cost extra. Guild doesn't publish a price list: plans are priced with the Guild team, and model usage is metered at list price.

### Can I move an agent from AgentCore to Guild?

Mostly by mapping. A Harness agent becomes a Native agent, Strands or LangGraph code becomes a TypeScript or LangGraph agent, Gateway tools become Guild integrations built from the same OpenAPI specs or MCP servers, and EventBridge schedules become schedule triggers. Strands interrupts become approval steps set in the Guild UI. Python agents with extra packages or direct network calls need changes.

## Sources

- [strandsagents.com/docs/user-guide/sdk/quickstart/typescript/index](https://strandsagents.com/docs/user-guide/sdk/quickstart/typescript/index.md)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.html)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness.html)
- [strandsagents.com/docs/user-guide/sdk/agents/structured-output/index](https://strandsagents.com/docs/user-guide/sdk/agents/structured-output/index.md)
- [strandsagents.com/docs/user-guide/sdk/multi-agent/multi-agent-patterns/index](https://strandsagents.com/docs/user-guide/sdk/multi-agent/multi-agent-patterns/index.md)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway-target-integrations.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway-target-integrations.html)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway-target-MCPservers.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway-target-MCPservers.html)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/mcp-getting-started.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/mcp-getting-started.html)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway-schema-openapi.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway-schema-openapi.html)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/key-features-and-benefits.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/key-features-and-benefits.html)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/policy-core-concepts.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/policy-core-concepts.html)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway-outbound-auth.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/gateway-outbound-auth.html)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness-vs-runtime.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness-vs-runtime.html)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-instances.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-instances.html)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/agentcore-vpc.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/agentcore-vpc.html)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-lifecycle-settings.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-lifecycle-settings.html)
- [aws.amazon.com/blogs/storage/orchestrating-multi-agent-ai-architectures-with-amazon-s3-files](https://aws.amazon.com/blogs/storage/orchestrating-multi-agent-ai-architectures-with-amazon-s3-files/)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-invoke-agent.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-invoke-agent.html)
- [aws.amazon.com/blogs/machine-learning/integrating-amazon-bedrock-agentcore-with-slack](https://aws.amazon.com/blogs/machine-learning/integrating-amazon-bedrock-agentcore-with-slack/)
- [strandsagents.com/docs/user-guide/sdk/interrupts/index](https://strandsagents.com/docs/user-guide/sdk/interrupts/index.md)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/security\_iam\_service-with-iam.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/security_iam_service-with-iam.html)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness-operations.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness-operations.html)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/policy-guardrails-getting-started.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/policy-guardrails-getting-started.html)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/release-notes.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/release-notes.html)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/evaluations.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/evaluations.html)
- [aws.amazon.com/about-aws/whats-new/2025/07/ai-agents-tools-aws-marketplace](https://aws.amazon.com/about-aws/whats-new/2025/07/ai-agents-tools-aws-marketplace/)
- [docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness-skills.html](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/harness-skills.html)
- [github.com/aws/agentcore-cli](https://github.com/aws/agentcore-cli)
- [aws.amazon.com/bedrock/agentcore/pricing](https://aws.amazon.com/bedrock/agentcore/pricing/)
- [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. 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)
- [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)