Managed Agents
A managed agent execution framework provided by Anthropic that allows developers to manage and run automated AI agent sessions in the cloud. It supports session state management, error handling, and tool invocation within agent workflows.
Core Facts
Managed Agents refers to agents whose lifecycle is managed by the platform; developers can configure persistent memory stores, permission policies, and cross-session context without managing state storage themselves.
The free credit can be used for the Claude API, Agent SDK, Managed Agent and Playground.
Workflow is deterministic: developers pre-define the node sequence and data flow paths, making the execution process predictable and traceable.
Timeline (last 90 days)
The free credit can be used for the Claude API, Agent SDK, Managed Agent and Playground.
v2.1.304 adds the /claude-api managed-agents-secure command, which compares the Managed Agents proxy settings item by item with Anthropic's public security guidelines without making any modifications.
The documentation improves the headers descriptions for Managed Agents and telemetry endpoints, and adds a note that the speed parameter requires a beta header.
Philip demonstrated AI Talk Radio, a talk show generator powered by Managed Agents, where the system starts an environment, automatically installs Python dependencies, reads skill files, then researches, writes a script, generates music and speech, and mixes the output; the app is freely available in AI Studio's Gallery, and users can remix it.
Claude Opus 5.5's ecosystem includes Claude Code, Agent SDK, Managed Agents, and it can be used on Amazon Bedrock, Google Cloud, and Microsoft Foundry, supporting long tasks running up to 18 hours.
Claude Opus 5.5's ecosystem includes Claude Code, Agent SDK, Managed Agents, and it can be called on Bedrock, Google Cloud, and Microsoft Foundry.
Claude Opus 5.5's ecosystem includes Claude Code, Agent SDK, Managed Agents, availability on Bedrock/Google Cloud/Microsoft Foundry, plus a year's accumulation of third-party integrations.
Anthropic's Managed Agents has launched a public beta of Dynamic Workflows
v1.13.0 added three capabilities to Managed Agents: workflows, multiagent configuration, and thread status filtering.
The managed-agent approach reduces cold-start costs and naturally fits cloud-based elastic scaling scenarios, at the cost of some control over underlying execution details.
9 more timeline events
All Facts (20)
Managed Agents refers to agents whose lifecycle is managed by the platform; developers can configure persistent memory stores, permission policies, and cross-session context without managing state storage themselves.
75%VerifiedThe free credit can be used for the Claude API, Agent SDK, Managed Agent and Playground.
65%VerifiedWorkflow is deterministic: developers pre-define the node sequence and data flow paths, making the execution process predictable and traceable.
65%UnverifiedManaged Agents启动的Agent能在自己隔离的Linux环境中执行代码
90%UnverifiedClaude Opus 5.5's ecosystem includes Claude Code, Agent SDK, Managed Agents, and it can be called on Bedrock, Google Cloud, and Microsoft Foundry.
60%UnverifiedThe documentation improves the headers descriptions for Managed Agents and telemetry endpoints, and adds a note that the speed parameter requires a beta header.
50%UnverifiedClaude Opus 5.5's ecosystem includes Claude Code, Agent SDK, Managed Agents, and it can be used on Amazon Bedrock, Google Cloud, and Microsoft Foundry, supporting long tasks running up to 18 hours.
50%UnverifiedClaude Opus 5.5's ecosystem includes Claude Code, Agent SDK, Managed Agents, availability on Bedrock/Google Cloud/Microsoft Foundry, plus a year's accumulation of third-party integrations.
50%Unverifiedv1.13.0 added three capabilities to Managed Agents: workflows, multiagent configuration, and thread status filtering.
50%UnverifiedThe managed-agent approach reduces cold-start costs and naturally fits cloud-based elastic scaling scenarios, at the cost of some control over underlying execution details.
50%UnverifiedThe evaluated_permission enum in Managed Agents-related events now shares a single definition across multiple events.
50%UnverifiedModules such as the Dreams API, User Profiles API, and Managed Agents are not part of Claude's core conversation API, but are components of the higher-level Agent infrastructure that Anthropic is building.
50%UnverifiedThe event list filter for Managed Agents added typed event type values.
50%Unverifiedv2.1.304 adds the /claude-api managed-agents-secure command, which compares the Managed Agents proxy settings item by item with Anthropic's public security guidelines without making any modifications.
50%UnverifiedAnthropic's Managed Agents has launched a public beta of Dynamic Workflows
50%Unverifiedv1.12.0 adds a url_sources parameter to the web_fetch tool configuration for hosted Agents.
50%Unverifiedv1.6.0 added auto mode tool permissions for Managed Agents, allowing managed agents to manage tool call permissions in automatic mode.
70%UnverifiedThe new version supports mounting public GitHub repositories in Managed Agents sessions without requiring an authorization_token.
50%Unverifiedv1.10.0 fixes the session tool runner so that it stops after any end-of-turn idle (issue #969).
50%Unverifiedv1.10.0 adds a rejection stop reason and a stop_details field to session idle events for Managed Agents.
50%