Contents
Running an agent in production means standing up the agent loop, tool execution, a sandbox, and state persistence—all yourself. Claude Managed Agents takes that whole burden off your hands: Anthropic runs it for you. Launched as a public beta on April 8, 2026, it's a suite of composable APIs for building and deploying cloud-hosted agents at scale.
This article covers, based on official information, what Managed Agents is, how it differs from the self-hosted Agent SDK, persistent memory and "dreaming," outcomes-based grading and multi-agent, and pricing. The key points up front. ① Instead of "building your own agent loop," you get a fully managed environment where Claude can read files, run commands, browse the web, and execute code securely. ② It has workspace-scoped persistent memory (mounted at /mnt/memory), which a "dream" can reorganize and consolidate. ③ Pricing is tokens + $0.08 per session-hour.
Anthropic owns the whole "run side"
— loop, sandbox, state, and memory on managed infrastructure
/mnt/memoryYou focus on defining the agent. Pricing is tokens + $0.08 per session-hour (only while running, metered to the millisecond).
1. What are Managed Agents?
In Anthropic's words, Managed Agents is "a suite of composable APIs for building and deploying cloud-hosted agents at scale," and the docs describe it as a "pre-built, configurable agent harness that runs in managed infrastructure." The core: "Instead of building your own agent loop, tool execution, and runtime, you get a fully managed environment where Claude can read files, run commands, browse the web, and execute code securely." Prompt caching, context compaction, sandboxing, and state persistence are built in from the start.
It's organized around four concepts—Agent (the definition) / Environment (where it runs) / Session / Events. The Environment can be an Anthropic-managed cloud sandbox or a self-hosted sandbox on your own infrastructure.
2. vs the Agent SDK (self-hosted vs managed)
The easy thing to conflate is the difference from the Claude Agent SDK. The two are a pair along the axis of "you run it" vs "Anthropic runs it."
- Your own harness in Python / TypeScript
- You operate the loop, tools, and runtime
- Infrastructure and scale are your responsibility
- Full control over the details
- Loop, sandbox, and state are on the managed side
- Persistent memory and dreaming are built in
- Billed on runtime ($0.08/hour)
- Focus on the definition, hand off operations
In short: "want to build your own engine? Agent SDK. Want to rent the engine and focus on the content? Managed Agents." They aren't competitors—they're a choice about how much of the operations you hold yourself. For the concept of agents, see what is multi-agent; for building one, how to build a multi-agent system.
3. Persistent memory and "dreaming"
A signature feature of Managed Agents is persistent memory (a memory store). It's "a workspace-scoped collection of text documents," mounted as a directory (/mnt/memory/) inside the session's sandbox. The agent reads and writes it with normal file operations, and the contents persist across sessions. Every change creates an immutable memory version for auditing (30-day retention). Limits: 100 kB per memory, 2,000 memories per store, 8 stores per session.
More unusual is "dreaming." Per the official description: "A dream reads an existing memory store alongside past session transcripts, then produces a new, reorganized memory store: duplicates merged, stale or contradicted entries replaced with the latest value, and new insights surfaced." It's an async job (1–100 input sessions, with optional instructions) that requires a dedicated beta header.
⚠️ Accuracy note: dreaming is a research preview requiring an access request. Some write-ups call it a "scheduled process," but the official docs describe it as an on-demand async job you create and poll. It's accurate to think of it as "a consolidation process you can run on a schedule," and this article does not assert that "Anthropic runs it automatically."
4. Outcomes grading and multi-agent
A newer feature is outcomes-based grading. Per Anthropic: "You write a rubric describing what success looks like and the agent works toward it. A separate grader evaluates the output against your criteria in its own context window." Anthropic reports it "improved task success by up to 10 points over a standard prompting loop" (+8.4% for docx, +10.1% for pptx—figures Anthropic published). Public beta.
Multi-agent orchestration is also built in: "A lead agent breaks the job into pieces and delegates each one to a specialist with its own model, prompt, and tools," running in parallel on a shared filesystem. The design philosophy of orchestrating agents echoes how to build a multi-agent system.
5. Pricing and availability
Pricing has two dimensions: ① tokens (standard model rates, with prompt caching applied) + ② session runtime at $0.08 per session-hour. Runtime is metered to the millisecond and billed only while status is running (idle or rescheduling is free). Anthropic's worked example: a 1-hour Opus 4.8 session is about $0.705.
| Item | Details |
|---|---|
| Launch | April 8, 2026 · public beta (enabled by default for all API accounts) |
| Access | Via Claude Console / Platform CLI / Claude Code |
| Pricing | Tokens + $0.08 / session-hour (only while running, metered to the ms) |
| Caveat | Stateful by design, so not eligible for Zero Data Retention (ZDR) or a HIPAA BAA |
| Memory / dream | dreaming is a research preview (access request required) |
Summary
Claude Managed Agents is a fully managed environment where Anthropic operates the agent loop, tool execution, sandbox, and state persistence for you. Where the self-hosted Agent SDK means "you run the engine," Managed Agents means "Anthropic runs it, and you focus on the definition"—a paired choice that differs in where operational responsibility sits.
Its hallmarks are workspace-scoped persistent memory (mounted at /mnt/memory, persisting across sessions) and "dreaming" (research preview) to reorganize and consolidate it, plus outcomes-based grading and multi-agent orchestration. Pricing is tokens + $0.08 per session-hour, available to all API accounts as an April 2026 public beta (stateful, so not eligible for ZDR / HIPAA BAA). Related: Agent SDK guide, what is multi-agent, how to build a multi-agent system.
FAQ
Q. What are Managed Agents?
A. Anthropic's suite of APIs for building and deploying cloud-hosted agents. Instead of building your own agent loop, tool execution, and runtime, you get a fully managed environment where Claude can read files, run commands, browse the web, and execute code securely. Prompt caching, compaction, sandboxing, and state persistence are built in. It launched as a public beta on April 8, 2026.
Q. How does it differ from the Agent SDK?
A. In who owns operations. The Agent SDK is a self-hosted harness you run in Python / TypeScript, where you operate the loop, tools, and infrastructure. Managed Agents has Anthropic provide the loop, sandbox, state, and memory on managed infrastructure, and you focus on defining the agent. They're not competitors—it's a choice about how much of the operations you keep.
Q. What are persistent memory and "dreaming"?
A. Persistent memory (a memory store) is a workspace-scoped collection of text documents, mounted in the sandbox as /mnt/memory/; the agent reads and writes it with normal file operations and it persists across sessions. "Dreaming" is an async job that reads the existing memory and past session transcripts to produce a reorganized memory store—merging duplicates, updating stale values, and surfacing new insights. Dreaming is currently a research preview (access request required).
Q. How much does it cost?
A. Two dimensions: token charges + session runtime at $0.08 per session-hour. Runtime is metered to the millisecond and billed only while status is running (idle / rescheduling is free). Anthropic's estimate is about $0.705 for a 1-hour Opus 4.8 session. Tokens use standard model rates with prompt caching.
Q. Can anyone use it?
A. It's a public beta from April 8, 2026, enabled by default for all API accounts, accessible via Claude Console / Platform CLI / Claude Code. But because it's stateful by design, it's not eligible for Zero Data Retention (ZDR) or a HIPAA BAA. Note also that features differ by stage—dreaming is a research preview requiring an access request (check the official docs for the latest).
