Skip to content

Blocks.ai publishes this comparison and sells in this market. Every claim about another product links to a public source.

Amazon Bedrock AgentCore vs Zenity

Amazon Bedrock AgentCore

AWS platform for building, deploying, and operating AI agents

Zenity AI Agent Security & Governance Platform

Security and governance platform for AI agents, aimed at security teams

Short answer

Amazon Bedrock AgentCore is AWS’s platform for building, deploying, and operating agents; Zenity is a security and governance platform that, it says, lets security teams discover agents and enforce policies.⁠Source 1, Source 2, Source 3 AgentCore hosts agents and can check Gateway calls against policies, while Zenity says it can block actions on Copilot Studio, Microsoft Foundry, and coding agents.⁠Source 1, Source 4, Source 5

Where each one sits

Six layers of running AI agents at a company, and what each product’s own public sources say it covers.

These aren’t the same kind of product

Where they overlap
AgentCore keeps an inventory of agents, applies rules to their actions, and logs their activity, and Zenity says it does too.⁠Source 4, Source 6, Source 7, Source 8, Source 9
Where they differ
Teams can also build and run agents on AgentCore.⁠Source 1, Source 10, Source 11 Zenity says it scans an organization’s environment and catalogs agents, including ones in SaaS platforms or on laptops.⁠Source 8
Running both
Zenity describes how it secures agents in Amazon Bedrock AgentCore.⁠Source 12, Source 13
Public sources · checked 2 October 2026
  • Offered
  • Not publicly documented

Amazon Bedrock AgentCore

  • Build agents: OfferedHarness managed agent loop⁠Source 1
  • Host and run agents: OfferedAgentCore Runtime⁠Source 1
  • Identity and access: OfferedAgentCore Identity workload identities⁠Source 14
  • Registry and governance: OfferedAWS Agent Registry with approvals⁠Source 6
  • Traffic between agents, tools, and models: OfferedAgentCore Gateway⁠Source 15
  • Agents across organizations: OfferedRegistry shared through AWS RAM⁠Source 16

Zenity

  • Build agents: Not publicly documented
  • Host and run agents: Not publicly documented
  • Identity and access: Not publicly documented
  • Registry and governance: OfferedAI Observability agent inventory⁠Source 8
  • Traffic between agents, tools, and models: OfferedTool-call blocking for coding agents⁠Source 17
  • Agents across organizations: Not publicly documented

At a glance

TopicAmazon Bedrock AgentCoreZenity
What it isA managed AWS platform for building, deploying, and operating agents, made of modular services used together or independently.⁠Source 1Software as a service.⁠Source 2 Zenity describes three layers: Surface (what an agent can reach and what’s exploitable), Enforce (stopping unsafe actions as decisions are made), and Protect (catching what slips through).⁠Source 3
Who it’s forOrganizations moving agents built with open-source or custom frameworks from proof of concept to production.⁠Source 11Security teams that need to discover and inventory agents, enforce policies, and reduce unmanaged risk, per Zenity.⁠Source 3
Agents it works withAgents in AgentCore Runtime, plus agents on premises or in other clouds through registry records, identities, and extra telemetry setup.⁠Source 1, Source 18, Source 19Zenity says it covers agents in Microsoft Copilot Studio, ChatGPT Enterprise, and Salesforce Agentforce, homegrown agents, coding agents, and AgentCore agents.⁠Source 8, Source 12, Source 17
Pricing modelConsumption-based, with no upfront commitment or minimum fee.⁠Source 20Custom pricing by private offer on its main AWS Marketplace listing; a separate Security Hub Extended listing shows list prices.⁠Source 2, Source 21
Available sinceGenerally available since October 2025; AWS Agent Registry since August 2026.⁠Source 22Zenity announced Azure Marketplace availability in March 2025 (Microsoft has since unified it into Microsoft Marketplace) and AWS Marketplace availability in January 2026.⁠Source 23, Source 24, Source 25

What each one is

Amazon Bedrock AgentCore

Amazon Bedrock AgentCore is AWS’s platform for building, deploying, and operating agents with any framework and model.⁠Source 1 Its modular services, such as Runtime, Gateway, Identity, Policy, and AWS Agent Registry, work together or independently.⁠Source 1, Source 4, Source 6, Source 14, Source 26 Customers use it without managing infrastructure.⁠Source 1

Zenity AI Agent Security & Governance Platform

Zenity AI Agent Security & Governance Platform is delivered as SaaS; Zenity says it lets security teams discover and inventory agents and enforce policies.⁠Source 2, Source 3 Zenity’s listing says it spans SaaS, home-grown cloud platforms, and end-user devices.⁠Source 2 Zenity describes three layers: Surface, Enforce, and Protect.⁠Source 3

The differences that matter

  1. How each one reaches agents

    Amazon Bedrock AgentCore

    Agents can run in AgentCore Runtime, a serverless environment, or sit elsewhere behind a Gateway that forwards requests to their HTTP endpoint.⁠Source 1, Source 15

    Zenity

    Zenity says agents emitting OpenTelemetry or gen_ai spans can connect, with an Evaluate API for inline enforcement; coding agents use agent hooks.⁠Source 17, Source 27

  2. How agents get into the inventory

    Amazon Bedrock AgentCore

    Teams publish records to AWS Agent Registry behind an approval workflow; with AWS Organizations, it can record Runtimes and Gateways it detects in member accounts.⁠Source 6, Source 28

    Zenity

    Zenity says AI Observability scans the environment, catalogs agents with their permissions and tool access, and flags agents outside sanctioned deployment channels.⁠Source 8

    People and AI agents can search AWS’s registry, including through an MCP endpoint.⁠Source 6 Searching Zenity’s inventory to call agents isn’t in Zenity’s public docs; its product docs require a login.⁠Source 29

  3. Controlling what agents do

    Amazon Bedrock AgentCore

    Policy can check each request through an AgentCore Gateway against policies, written in natural language or Cedar, before allowing tool access.⁠Source 4

    Zenity

    Zenity says Boundaries can check agent actions in real time.⁠Source 9 It says it can block actions on Copilot Studio, Microsoft Foundry, and coding agents.⁠Source 5

    Zenity says Boundaries policies can be managed as version-controlled files through a command-line interface.⁠Source 27 AgentCore Policy logs its decisions for compliance and troubleshooting.⁠Source 4

For security teams

What a security review asks, answered from each vendor’s public documentation.

TopicAmazon Bedrock AgentCoreZenity
Network exposureCallers in a VPC can reach AgentCore over PrivateLink; AgentCore can reach private VPC resources without exposing them publicly.⁠Source 30, Source 31Delivered as SaaS.⁠Source 2 Network requirements for connected agents aren’t in Zenity’s public docs; its product docs require a login.⁠Source 29
IdentityWorkload identities in AgentCore Identity; inbound JWT authorization works with OAuth 2.0 providers such as Entra ID or Okta.⁠Source 11, Source 14, Source 32Zenity says Boundaries rules can reference Okta attributes such as active status, role, department, and job title.⁠Source 9
Access changes and revocationExplicit deny overrides other policies on Runtime, Gateway, and Memory; removing an account from a registry share revokes its access.⁠Source 16, Source 33Zenity says its kill switch immediately disables an agent’s tool and data access.⁠Source 9 It says Prevent-mode rules hard-stop actions.⁠Source 9
Audit trailCloudTrail can log Gateway calls (data events are off by default) and logs Registry control-plane calls; Policy logs its decisions.⁠Source 4, Source 28, Source 34, Source 35Zenity says it logs agent messages and tool calls, and can stream audit log events to Splunk or Microsoft Sentinel.⁠Source 8, Source 27
ComplianceHIPAA eligible; AWS lists it as FedRAMP (Class C and Class D), SOC 2, ISO 27001:2022, and CSA STAR compliant.⁠Source 36, Source 37Zenity says it holds SOC 2 Type II and ISO 27001 compliance; FedRAMP “In Process” was announced in March 2026.⁠Source 38, Source 39

Full comparison

18 criteria in five groups. Every cell links to its source, or says no public source answers it.

Amazon Bedrock AgentCore and Zenity compared on 18 criteria
Amazon Bedrock AgentCoreZenity
What it is
What it is and who it’s forAWS platform for building, deploying, and operating agents with any framework and model, made of modular services used together or independently.⁠Source 1Zenity’s listing: a security and governance platform for AI agents across SaaS, cloud, and endpoints.⁠Source 2 Zenity says it lets security teams inventory agents.⁠Source 3
MaturityGenerally available since October 2025.⁠Source 22 Policy since March 2026, and AWS Agent Registry since August 2026.⁠Source 22Zenity announced AWS Marketplace availability in January 2026.⁠Source 25 It says GitHub Copilot and OpenAI Codex coverage reached GA in August 2026.⁠Source 27
Control
Agent registry and discoveryAWS Agent Registry catalogs agents, MCP servers, tools, and skills behind an approval workflow, including ones on premises or in other clouds.⁠Source 1, Source 6Zenity says AI Observability scans and catalogs agents in SaaS platforms, custom builds, and on laptops, with their permissions and tool access.⁠Source 8
Identity and access controlWorkload identities in AgentCore Identity.⁠Source 14 Inbound JWT authorization works with any OAuth 2.0 compatible provider; IAM SigV4 is the Runtime default.⁠Source 32, Source 40Zenity says Boundaries rules can reference Okta attributes such as active status, role, department, and job title.⁠Source 9
Ownership, policy, and revocationFor Gateway traffic, policies in natural language or Cedar set which tools an agent can call, and when.⁠Source 4 Curators can deprecate registry records.⁠Source 28Zenity says it can block actions on Copilot Studio, Microsoft Foundry, and coding agents.⁠Source 5 It says posture policies can alert, block, or remediate.⁠Source 41
Audit log and observabilityMetrics, spans, and logs go to CloudWatch.⁠Source 7 CloudTrail can log Gateway calls (data events are off by default) and logs Registry control-plane calls.⁠Source 28, Source 34, Source 35Zenity says it logs agent messages, tool calls, retrievals, and handoffs.⁠Source 8 It says audit log events can stream to Splunk or Microsoft Sentinel.⁠Source 27
Connection
How agents connectAgents can run in serverless AgentCore Runtime.⁠Source 1 Gateway can forward to any HTTP endpoint, and AgentCore can reach private VPC resources.⁠Source 15, Source 31Zenity says OpenTelemetry agents can connect, with an Evaluate API for enforcement; coding agents use agent hooks.⁠Source 17, Source 27 Network needs aren’t in Zenity’s public docs.
Agents across organizationsThrough AWS RAM, other AWS accounts can discover, publish, or administer registry records.⁠Source 16 Those outside the owner’s AWS Organization must accept an invitation.⁠Source 16Not in Zenity’s public docs; its product docs require a login (checked 2 October 2026)⁠Source 29
Protocol supportRuntime agents can serve HTTP, MCP, A2A, or AG-UI.⁠Source 42 Gateway acts as one MCP server over its MCP targets; the Registry checks records against MCP and A2A schemas.⁠Source 28, Source 43Zenity says custom agents use OpenTelemetry and AIDR shows agent-to-agent requests and responses.⁠Source 27, Source 44 Whether Zenity supports A2A isn’t publicly documented.
Frameworks, models, and clouds supportedRuntime works with CrewAI, LangGraph, LlamaIndex, Google ADK, OpenAI Agents SDK, Strands Agents, and custom frameworks, and models in or outside Bedrock.⁠Source 1Zenity says discovery covers homegrown agents built on Azure AI Foundry, AWS Bedrock, or Google Vertex AI, and OpenTelemetry agents can connect.⁠Source 8, Source 27
Operations
Deployment options and data residencyAWS says cross-region inference can move Memory, Policy, and Evaluations prompts out of the primary Region; AgentCore may store content to improve your service.⁠Source 1, Source 45Software as a service, deployed on AWS per its AWS Marketplace listing.⁠Source 2 Hosting regions and self-hosting aren’t in Zenity’s public docs.
Compliance attestationsAWS lists AgentCore as FedRAMP (Class C and Class D) compliant.⁠Source 36, Source 37 It is HIPAA eligible, and SOC 2, ISO 27001:2022, and CSA STAR compliant.⁠Source 22, Source 36Zenity says it holds SOC 2 Type II and is ISO 27001 compliant.⁠Source 38 It announced FedRAMP “In Process” status in March 2026; authorization is pending.⁠Source 39
Support and SLAAWS says the Amazon Bedrock SLA applies to AgentCore.⁠Source 11 Basic Support is included for all AWS customers.⁠Source 46Zenity’s subscription terms commit to at least 99.9% monthly uptime, on a commercially reasonable efforts basis.⁠Source 47 Requests go via Zendesk in business hours.⁠Source 47
Time and effort to get runningAn AWS account with credentials, and permissions to call AgentCore and assume CDK bootstrap roles.⁠Source 10 The CLI scaffolds, tests locally, and deploys an agent.⁠Source 10Zenity describes step-by-step guides for connecting custom agents via Cribl, LiteLLM, and Kong; its Cursor plugin installs in Cursor desktop.⁠Source 27, Source 48
Pricing model and public pricesConsumption-based, no upfront commitment or minimum fee.⁠Source 20 Registry: 5,000 records free a month, then $0.400 per 1,000 records.⁠Source 20Main AWS Marketplace listing: custom pricing by private offer.⁠Source 2 Security Hub Extended listing: $130 per resource a month for Observability.⁠Source 21
Building
Agent building toolsHarness: a managed agent loop set by model, prompt, and tools.⁠Source 1 Or write the loop with a framework such as Strands, LangGraph, or Google ADK.⁠Source 10Not in Zenity’s public docs; its product docs require a login (checked 2 October 2026)⁠Source 29
Model accessModel-agnostic: AWS names OpenAI, Gemini, Claude, Amazon Nova, Meta Llama, and Mistral models, in or outside Amazon Bedrock.⁠Source 11Zenity says AIDR pairs rules mapped to OWASP LLM and MITRE ATLAS with LLM-based detections.⁠Source 44 The models it uses aren’t in Zenity’s public docs.
Integrations and ecosystemGateway offers 1-click integrations with tools such as Salesforce, Slack, Jira, Asana, and Zendesk; AWS Marketplace partner tools can be imported.⁠Source 11, Source 26Zenity says it integrates with Microsoft Agent 365 and AWS Security Hub Extended and is on the Cursor Marketplace.⁠Source 48, Source 49, Source 50 It announced a ServiceNow SecOps partnership.⁠Source 51

Which to choose

Choose Amazon Bedrock AgentCore if

  • You want to build and run agents on AWS, writing the loop with frameworks such as Strands, LangGraph, or Google ADK.⁠Source 1, Source 10
  • You want a registry where teams publish agents, MCP servers, and tools behind an approval workflow, searchable by people and agents.⁠Source 6
  • You want to share that registry with other AWS accounts, choosing whether each can discover, publish, or administer records.⁠Source 16
  • You want private networking: callers in a VPC reach AgentCore over PrivateLink, without an internet gateway or NAT device.⁠Source 30

Choose Zenity if

  • Your agents live in platforms such as Copilot Studio, ChatGPT Enterprise, and Agentforce, where Zenity says it builds an inventory.⁠Source 8
  • You want what Zenity says it offers: posture policies that alert, block, or remediate automatically, and ownership shown for every discovered agent.⁠Source 41
  • You need coding agents such as Claude Code and Cursor covered; Zenity says it covers them and can block dangerous tool calls.⁠Source 17
  • You want audit events in Splunk or Microsoft Sentinel and findings in AWS Security Hub Extended, which Zenity says it supports.⁠Source 27, Source 50

Questions buyers ask

Can either one build or host agents?

AgentCore can: developers write the agent loop with a framework such as Strands or LangGraph and deploy it to serverless Runtime.⁠Source 1, Source 10 Building or hosting agents in Zenity isn’t in its public docs; its product docs require a login.⁠Source 29

How is each one priced?

AgentCore pricing is consumption-based, with no upfront commitment or minimum fee.⁠Source 20 Zenity’s main AWS Marketplace listing is by private offer; its Security Hub Extended listing shows $130 per resource a month for Observability and $16 per million tokens a month for Runtime Protection.⁠Source 2, Source 21

Do they support MCP and A2A?

AgentCore Runtime can host MCP and A2A servers, and AWS Agent Registry checks records against the MCP and A2A schemas.⁠Source 28, Source 42 Zenity says its Cursor plugin maps each Cursor agent to the MCP endpoints it uses.⁠Source 48 Whether Zenity supports A2A isn’t publicly documented.

Can either one connect agents across organizations?

AgentCore can share a registry with other AWS accounts through AWS RAM; accounts outside your AWS Organization must accept an invitation.⁠Source 16 Reaching agents a partner owns, with access the partner controls, isn’t in Zenity’s public docs; its product docs require a login.⁠Source 29

How we compare

Read the full method

Every claim on this page links to a public source. Where none answers a question, the page says so.

We re-check every fact at least every 90 days. This page was last checked .

Something wrong or out of date? Tell us and we’ll correct it.

Sources

59 public sources, each with the date we checked it. Every one opens in a new tab.

  1. Source 1: Overview - Amazon Bedrock AgentCore (Developer Guide) AWS · checked Back:abcdefghijklmnopqrs

  2. Source 2: AWS Marketplace: Zenity Zenity · checked Back:abcdefghij

  3. Source 3: Platform | AI Agent Security & Governance Platform | Zenity Zenity · checked Back:abcdef

  4. Source 4: Policy in Amazon Bedrock AgentCore: Control Agent Interactions AWS · checked Back:abcdefg

  5. Source 5: Zenity's Coverage of the 2026 OWASP Top 10 for LLM Apps Zenity · checked Back:abc

  6. Source 6: AWS Agent Registry: Discover and manage agents, tools, and resources AWS · checked Back:abcdefg

  7. Source 7: Observe your agent applications on Amazon Bedrock AgentCore Observability AWS · checked Back:ab

  8. Source 8: AI Observability | See Every Agent, Know What it Touches | Zenity Zenity · checked Back:abcdefghij

  9. Source 9: Runtime Boundaries | The Runtime Boundary for Autonomous AI | Zenity Zenity · checked Back:abcdef

  10. Source 10: Get started with Amazon Bedrock AgentCore AWS · checked Back:abcdef

  11. Source 11: Amazon Bedrock AgentCore FAQs AWS · checked Back:abcdef

  12. Source 12: Amazon Bedrock AgentCore Security | Full-Lifecycle Control Zenity · checked Back:abc

  13. Source 13: Inside the Agent Stack: Securing Agents in Amazon Bedrock AgentCore Zenity · checked Back:ab

  14. Source 14: Provide identity and credential management for agent applications with Amazon Bedrock AgentCore Identity AWS · checked Back:abcd

  15. Source 15: HTTP passthrough targets - AgentCore Gateway AWS · checked Back:abc

  16. Source 16: Sharing a registry across accounts with AWS RAM AWS · checked Back:abcdef

  17. Source 17: Coding and Personal Agents | Zenity Zenity · checked Back:abcde

  18. Source 18: Features of AgentCore Identity AWS · checked Back to text

  19. Source 19: Add observability to your Amazon Bedrock AgentCore resources AWS · checked Back to text

  20. Source 20: Amazon Bedrock AgentCore Pricing AWS · checked Back:abcd

  21. Source 21: AWS Marketplace: Zenity AI Security & Governance Platform for Security Hub Extended Zenity · checked Back:abc

  22. Source 22: Release notes - Amazon Bedrock AgentCore AWS · checked Back:abcd

  23. Source 23: Zenity Now Available in the Microsoft Azure Marketplace Zenity · checked Back to text

  24. Source 24: Introducing Microsoft Marketplace - Thousands of solutions. Millions of customers. One Marketplace. - The Official Microsoft Blog Zenity · checked Back to text

  25. Source 25: Zenity Now Available on AWS Marketplace, Bringing End-to-End Security to Amazon Bedrock AgentCore and Enterprise AI Agents Everywhere Zenity · checked Back:abc

  26. Source 26: Amazon Bedrock AgentCore Gateway: A secure AI gateway for agents, tools, and models AWS · checked Back:ab

  27. Source 27: From Triage to Full Coverage: The Shift AI Agent Security Took in August Zenity · checked Back:abcdefghij

  28. Source 28: Key capabilities - AWS Agent Registry AWS · checked Back:abcdef

  29. Source 29: Zenity Documentation (login) Zenity · checked Back:abcdef

  30. Source 30: Use interface VPC endpoints (AWS PrivateLink) with Amazon Bedrock AgentCore AWS · checked Back:ab

  31. Source 31: Connect to private resources in your VPC using VPC Lattice AWS · checked Back:ab

  32. Source 32: Configure inbound JWT authorizer AWS · checked Back:ab

  33. Source 33: Resource-based policies for Amazon Bedrock AgentCore AWS · checked Back to text

  34. Source 34: Log Amazon Bedrock AgentCore Gateway API calls with CloudTrail AWS · checked Back:ab

  35. Source 35: Enable CloudTrail data event logging for Amazon Bedrock AgentCore Gateway resources - Amazon Bedrock AgentCore AWS · checked Back:ab

  36. Source 36: Compliance validation for Amazon Bedrock AgentCore AWS · checked Back:abc

  37. Source 37: Federal Risk and Authorization Management Program (FedRAMP) - Services in Scope - Amazon Web Services AWS · checked Back:ab

  38. Source 38: Zenity Trust Center Zenity · checked Back:ab

  39. Source 39: Zenity Achieves FedRAMP “In Process” Status for AI Agent Security Zenity · checked Back:ab

  40. Source 40: Authenticate and authorize with Inbound Auth and Outbound Auth AWS · checked Back to text

  41. Source 41: AI Security Posture Management (AISPM) | Stop Agent Risk Before Deployment | Zenity Zenity · checked Back:ab

  42. Source 42: Understand the AgentCore Runtime service contract AWS · checked Back:ab

  43. Source 43: Supported targets for Amazon Bedrock AgentCore gateways AWS · checked Back to text

  44. Source 44: AI Detection and Response (AIDR) | See the Threat, Stop the Action | Zenity Zenity · checked Back:ab

  45. Source 45: Cross-region inference in AgentCore Memory, Policy in AgentCore, and AgentCore Evaluations AWS · checked Back to text

  46. Source 46: Compare AWS Support plans AWS · checked Back to text

  47. Source 47: Zenity Subscription Terms and Conditions (EULA linked from Zenity's AWS Marketplace listings) Zenity · checked Back:ab

  48. Source 48: Seeing Every MCP Connection: Zenity Joins the Cursor Marketplace Zenity · checked Back:abc

  49. Source 49: Zenity Now Integrates with Microsoft Agent 365 Zenity · checked Back to text

  50. Source 50: Zenity Selected for AWS Security Hub Extended to Secure Enterprise AI Agents Zenity · checked Back:abc

  51. Source 51: Zenity Announces Partnership with ServiceNow to Operationalize AI Agent Risk Reduction in SecOps Zenity · checked Back to text

  52. Source 52: Zenity Now Available on AWS Marketplace, Bringing End-to-End Security to Amazon Bedrock AgentCore and Enterprise AI Agents Everywhere Zenity · checked Back to text

  53. Source 53: Why Blocks? Blocks.ai · checked Back to text

  54. Source 54: What is Blocks? Blocks.ai · checked Back to text

  55. Source 55: Your company's private network Blocks.ai · checked Back to text

  56. Source 56: Network requirements Blocks.ai · checked Back to text

  57. Source 57: Solutions: Agent sprawl Blocks.ai · checked Back to text

  58. Source 58: Solutions: Partner networks Blocks.ai · checked Back to text

  59. Source 59: Pricing Blocks.ai · checked Back to text