AI Agent FactoryGitHub

AI Agent Factory

Enterprise samples for building, governing, and operating agentic AI on AWS with Amazon Bedrock and Amazon Bedrock AgentCore.

Find your projectGet started

One journey, four starting points

AI Agent Factory Atlas: four complementary projects for enterprise agentic AI on AWS. In the centre sits a hub labelled Agent Factory Capabilities: LLM Gateway, Tool Gateway, Identity and Registry, Policy and Observability. Around it, four stages in order. Learn: Workshop, hands-on platform patterns. Build: Visual Workflow Platform, drag-and-drop agent builder. Govern: MCP Governance Gateway, per-tool-call authorization. Scale: Enterprise Blueprint, multi-account reference blueprint. A legend distinguishes the sequential journey path, a skip-ahead path, and the shared-capability links from each project to the hub. A footer reads: Each project is self-contained. Start anywhere based on your role and goals.
  1. 1. LearnWorkshopLearn the platform patterns hands-on
  2. 2. BuildSelf-ServiceBuild and ship agents visually
  3. 3. GovernMCP GatewayGovern every tool call
  4. 4. ScaleBlueprintEvaluate the enterprise reference

Pick a project

Stage, audience, validated regions, first deploy and cost, every fact linked to its source. See the full comparison.

  • 1. LearnDetails

    Building an Enterprise Agentic AI Platform

    Learn the platform patterns hands-on

    Best for: Platform and ML engineers who want to understand and build the foundation.

    Validated regions
    AWS-run events: us-west-2. Self-paced: us-west-2 (default), us-east-1, or eu-west-1. Other regions are not supported. sourceThe contentspec.yaml deployableRegions list is us-west-2, us-east-1 and eu-west-1. Workshop Studio events provision the account in us-west-2 (content/introduction/getting-started/aws-event.en.md).
    First deploy
    About 30 to 45 minutes for the self-paced deploy script (five CloudFormation stacks) sourceThe self-paced guide (content/introduction/getting-started/self-service.en.md) notes that the Registry stack alone takes 20 to 30 minutes. At an AWS event the account arrives pre-provisioned, so there is nothing to deploy.
    Cost
    About $15 to $30 for a one-day run in us-west-2 (workshop estimate) sourceAt an AWS-run event the account is provided and the cost is covered. Cost accrues per hour whether or not the environment is in use.
  • 2. BuildDetails

    AgentCore Visual Workflow Platform

    Build and ship agents visually

    Best for: Engineers who want to build and ship agents fast on top of AgentCore.

    Validated regions
    Any AWS region; us-east-1 is the default sourceOutside us-east-1 the WAF web ACL is REGIONAL on the Cognito user pool and the CloudFront distribution runs without an edge ACL. APAC regions may need the model ID set explicitly.
    First deploy
    Roughly 15 to 20 minutes for a first-time deploy source
    Cost
    About $0.02 to $0.39 per month for the platform infrastructure at low to moderate usage (docs/COSTS.md estimate, us-east-1 list prices) sourceExcludes the WAF web ACL that infra/stacks/platform_stack.py always creates, which is billed separately and for which the repository publishes no figure, and all agent inference, AgentCore and vector-store usage.
  • 3. GovernDetails

    Enterprise MCP Governance Gateway

    Govern every tool call

    Best for: Platform and security engineers who need per-tool-call authorization and audit.

    Validated regions
    us-west-2 by default; configurable; no tested-regions list is published source
    First deploy
    About 5 minutes for the five quickstart steps; the gateway stack itself takes about 2 minutes source
    Cost
    not documentedThe README lists what the stack creates (AgentCore Gateway and policy engine, four Lambdas, a Cognito user pool, a Secrets Manager secret, a customer-managed KMS key, SSM parameters, and a Bedrock Guardrail) but publishes no cost figure.
  • 4. ScaleDetails

    Enterprise Agentic AI Platform Blueprint

    Evaluate the enterprise reference

    Best for: Platform and security engineers building enterprise-scale infrastructure.

    Validated regions
    Validated in eu-west-1; SCP allow-list us-west-2, us-east-1, eu-west-1 sourceThe SCP region allow-list comes from PLATFORM_APPROVED_REGIONS in packages/platform-baselines/src/approved-regions.ts. A different Region is a new validation target, not a configuration-only substitution.
    First deploy
    not documentedThe README documents the deployment sequence (sections 6.1 to 6.6: one-time setup, configuration, scoped bootstrap, Platform pipeline, Workstream onboarding, validation) but no duration.
    Cost
    not documentedREADME section 8 describes a two-layer cost model (shared Platform cost and Workstream cost) and recommended controls such as allocation tags, budgets and CUR reconciliation, but publishes no figure.

Who is this for?

Shared capabilities

Every project draws on the same capability contracts; the implementations are replaceable.

Before you deploy

Open advisories

What each advisory means for you

Real resources, real costs

Every project deploys real, billable AWS resources. Check the cost notes and teardown steps, the support envelope, and the license before you deploy.

Ready to start?

Get startedSource on GitHub