AWS services to run, govern and observe agents from any framework: Runtime, Gateway, Identity, Policy, Observability and Agent Registry.
Agent Control Planes
Registry, lifecycle, policy, and observability across a fleet of agents from many vendors.
An agent control plane answers: which agents exist, who owns them, what are they allowed to do, and are they healthy? Compare hyperscaler, SaaS-platform, and independent options on the scope of agents they can govern.
- In dataset
- 7
More filters
Major vendor tools
Tools from the major platform vendors are listed first; independent and open-source options follow below.
IBM agent platform whose Agentic Control Plane adds operations dashboards, policy and access governance, and a shared agent catalog.
Microsoft Agent 365
Microsoft
Control plane to observe, govern and secure an organization's AI agents via a central registry, Entra, Purview and Defender.
MuleSoft Agent Fabric
Salesforce (MuleSoft)
MuleSoft suite to register, route, govern and visualize agents, MCP servers and APIs across vendors using MCP and A2A.
ServiceNow AI Control Tower
ServiceNow
ServiceNow hub to discover, observe, govern, secure and measure AI models and agents, including those from other platforms.
Workday hub to register, govern and measure Workday, customer and partner AI agents alongside people and financial data.
Filtered open source and third-party tools
1 matching non-vendor tools in this filtered view.
Vendor-neutral control center to observe, govern, evaluate and track cost of agents built on many frameworks and platforms.
Important notes
Warning
Warning
Warning
Warning
Warning
Warning
Recent updates
See auto-detected changesAWS released the new AgentCore Runtime (V2) with consumption-based memory billing and about 2-second P75 cold starts, in five regions.
SourceIBM added an Agentic Control Plane to watsonx Orchestrate with operations dashboards, policy and access governance, and a shared agent catalog, on AWS and IBM Cloud.
SourceFrequently asked questions
What is an agent control plane?
The management layer for a fleet of agents: a registry of which agents exist and who owns them, lifecycle controls to publish, pause or retire them, policy that applies across vendors, and observability of health, usage, and cost. Analysts now evaluate it as a market of its own, and vendors such as Microsoft (Agent 365) and IBM use the same term.
Do I need one if I only use one cloud platform?
Each hyperscaler ships control-plane features for its own agents. The case for a separate control plane grows once agents come from several places — SaaS apps, low-code builders, and custom code on more than one cloud — because inventory and policy then have to span all of them.
How does this relate to agent identity and guardrails?
Control planes answer which agents exist and what policy applies across the fleet. Agent identity tools answer who an agent is and what it may access. Guardrails answer whether a specific prompt, output, or action is safe right now. Many products span two layers; each is listed once under its primary purpose.
Explore adjacent hubs
Compare the active category against the platform foundation layer, the cross-category updates feed, and the sourcing/contribution guide.
Review Microsoft Foundry, Amazon Bedrock, and Gemini Enterprise Agent Platform as the foundation layer behind this category.
Check the market-intelligence feed for high-impact moves, plus the expandable full log for releases, deprecations, acquisitions, and other notable changes.
See sourcing standards, contribution rules, and project scope before adding or updating tracked tools.