Claude Managed Agents

HostedWorkflow engine

Pre-built, configurable agent harness that runs in managed infrastructure. Best for long-running tasks and asynchronous work.

Homepage Docs Pricing

Scanned 12 Oct 2026 · Schema v5 · features v21

From: —
Usage based: model tokens plus running session time; server-side web search separately billed.
Free tier: Not documented
New users receive a small amount of free credits to test the API; amount not quantified. No ongoing free Managed Agents tier advertised.
Isolation: Container
shares the host kernel
Regions: —
Model inference geography supports global/US routing; sandbox/session storage regions or a regional availability map are not disclosed. Do not infer service regions from model routing or AWS sibling distribution.
Capabilities: 14 / 61
4 partial · 25 fail · 0 not assessed
Agent readiness: 10/11 · 10/11
read · drive, pre-login surface

Advertised for

Long running asynchronous coding/research/data/document tasks · Bash/file/Playwright tools in Linux containers · Remote MCP and custom tool integrations · Recurring scheduled agents and signed webhook triggers · Subagents, advisor model and dynamic workflow runs · Outcome graded iteration · Cross session memory; gated dreaming consolidation

Built for

Developers, then technical

· REST/SDK/CLI first
· Developer/Admin console roles
· Custom tools and cloud/self-host worker integration

01 Pricing Usage based: model tokens plus running session time; server-side web search separately billed.

Tier	EntryManaged Agents beta
Price	$0.08 per running session-hour + model tokens + applicable tools
Includes	Enabled by default for all API accounts; MCP tunnels and dreaming separately require research-preview access.
Compute hours overage	$0.08/h

Free tier: New users receive a small amount of free credits to test the API; amount not quantified. No ongoing free Managed Agents tier advertised.

Session-hour at $0.08, measured to millisecond while running; token rates vary by model/cache/speed/inference geography; web search $10/1,000 searches.·Card required: unconfirmed·platform.claude.com

Overages: Model token table applies. US-only inference 1.1x on supported models; fast-mode premium and prompt cache multipliers apply. No separate code-execution container-hour charge on top of session runtime.

02 Runtime Each fact carries its source; dots show confidence. Open a row for the evidence.

Isolation & lifecycle

Isolation primitive

Containershares the host kernel

Persistence

Stateful sessions retain conversation log, sandbox state and outputs across pauses; session deletion permanently deletes scoped files. Cross-session memory stores remain hosted, with text-document version history.

Snapshots / forks

Not documented

Resources & limits

Storage

Cloud sandbox disk up to 10 GB; memory up to 8 GB. Files API uploads can be mounted; session files downloadable. Memory stores hold cross-session text documents with version history.

Limits & quotas

Create endpoints 300/minute; read/list/stream endpoints 1,200/minute per organization; shared organization spend/rate limits apply. Cloud memory up to 8 GB, disk up to 10 GB. Memory stores cap at 10,000 memories. vCPU sizing and global maximum concurrent sessions not established by these pages.

GPU

Not documented

Access

Deploy interface

REST APIofficial ant CLIofficial client SDK beta methodsConsole visual builder

SDK languages

PythonTypeScriptC#GoJavaPHPRuby

Network & secrets

Egress controls

unrestricted, limited domain allowlists/package-manager/MCP allowances, or none; limited rules also constrain server-side web_search/web_fetch. API-created cloud default unrestricted; Studio-created default limited.

Secrets

Workspace-scoped per-user vault references; platform proxy handles external MCP tokens. Any API key with workspace access can reference vaults. Worker environment key scopes to work queue; per-session secret required for memory.

Bring your own cloud

Optional self-hosted sandbox workers execute tools in customer infrastructure; agent harness/control plane, session/work queue and memory remain Anthropic-hosted.

Placement & use

Jurisdiction

US/global model inference routing can be pinned by agent model config. Physical sandbox and session-storage region/residency are not disclosed here.

Advertised workloads

Long running asynchronous coding/research/data/document tasksBash/file/Playwright tools in Linux containersRemote MCP and custom tool integrationsRecurring scheduled agents and signed webhook triggersSubagents, advisor model and dynamic workflow runsOutcome graded iterationCross session memory; gated dreaming consolidation

03 Capabilities 14 pass · 4 partial · 25 fail · 61 of 61 assessed

Supported — Documented on the public surface and verified.
Partially supported — Exists with caveats: gated, thin, or enterprise-only.
Not supported — Checked and not offered.
Not assessed — Scanned before this capability was tracked. Not a lack.

Compute & storage 1/10

Persistent diskStorage that survives restart/stop (not ephemeral-only).

Partially supported

Object storageManaged S3-compatible / blob object store the platform PROVIDES to a user's workloads (buckets, presigned URLs). DISTINCT from persistent-disk (block/volume attached to an instance) and from a self-host dependency (source.self_host.deps[]=["object-storage"] is an infra dep to RUN an OSS tool — the opposite direction). SCOPE varies and matters: native first-class (Railway Buckets, Cloudflare R2) vs a sibling SKU / extension (Fly Tigris, Bunny Storage, DigitalOcean Spaces) — record which in the evidence quote / note. Admitted v15.

Not applicable

Snapshots / forkingSnapshot or copy-on-write fork of a running instance (filesystem-only counts). Whether the snapshot also restores memory + running processes is recorded separately by memory-snapshot (v19).

Not supported

Live-state (memory) snapshotsA snapshot / checkpoint / pause captures a running instance's MEMORY and PROCESS state and restores it, so running processes continue where they left off instead of a freshly booted instance with the same files. Counts whether user-triggered (snapshot, checkpoint, pause-to-storage) or used to restore pre-initialised state (memory snapshots for fast cold starts). Distinct from snapshots-forks (any snapshot or fork, including filesystem-only; a product passing that key may still fail this one) and from scale-to-zero (an idle-cost property; suspension may or may not keep memory). Actor multiplexing (see scale-to-zero) records its live-state half here — only when the suspended actor's MEMORY/process state is what comes back, not a freshly booted worker with the actor's files.

Not supported

Scale to zeroIdle instances suspend at no / negligible cost. ACTOR MULTIPLEXING (many suspended stateful actors sharing a small pool of pre-warmed workers, woken on request — Agent Substrate, AX, kagent; Rivet's hibernating actors) has NO key of its own (proposal REJECTED v20) — score the idle-cost half HERE and the live-state half under memory-snapshot; the oversubscription ratio / density is a performance characteristic the registry does not key.

Supported

GPU computeGPU-backed instances available.

Not supported

Multi-regionCompute placeable in more than one geographic region.

Not supported

Sandbox templates / custom imagesBuild reusable sandbox/VM images from an OCI image or Dockerfile (a base you fork instances from).

Not supported

Cloud-init / ignition configCustomise a VM / microVM / instance at boot via cloud-init (or ignition) user-data — the same boot-metadata interface as AWS/Azure/GCP. Inject packages, users, SSH keys, files, and run-commands declaratively at launch. Distinct from sandbox-templates (a PREBUILT image you fork instances from) — this is PER-LAUNCH declarative customisation, not a baked image.

Not supported

Desktop / computer-use sandboxA virtual desktop (GUI) for LLM computer-use — browser + desktop automation, often via noVNC/VNC.

Not supported

Selectable isolation runtimeThe user chooses the isolation runtime per workload / environment / sandbox from more than one option (e.g. microVM vs gVisor vs plain container, native namespaces vs gVisor, gVisor vs VM). Records the CHOICE; the isolation_primitive facet still records the best-evidenced primary. A platform that switches runtime automatically without a user choice (e.g. gVisor forced for GPU) does not pass on that alone.

Not supported

Networking & delivery 1/3

Automatic HTTPSTLS endpoints provisioned automatically per workload.

Not applicable

Built-in reverse proxyPlatform routes external traffic to workload services.

Not applicable

Custom domainsBring-your-own domain via CNAME/DNS.

Not applicable

Public preview URLsShareable per-deploy / per-branch URLs.

Not applicable

Direct public IPv6Per-instance stable public IPv6 for raw TCP/UDP (beyond a managed HTTPS proxy) — e.g. mosh / raw sockets.

Not supported

Egress controlsConfigurable OUTBOUND network policy — egress firewall / allowlist / egress proxy on traffic LEAVING a workload. Scoped to OUTBOUND only (v15): private-network REACHABILITY between a user's own services is private-networking, not this. Static-egress-IP belongs here (an outbound concept).

Supported

Private networkingA platform-internal private network between a user's OWN services — service-to-service connectivity, VPC, service mesh, and/or service discovery, not exposed to the public internet. DISTINCT from egress-controls (OUTBOUND firewall/allowlist), reverse-proxy (PUBLIC inbound ingress), and direct-ipv6 (per-instance PUBLIC addressing). Admitted v15.

Not supported

Email send / receiveSend and/or receive email from the workload.

Not applicable

Edge KV storeA globally-replicated key-value store read from WITHIN an edge runtime at the PoP (low-latency, eventually-consistent) — Cloudflare Workers KV, Deno KV, Fastly KV Store, Akamai EdgeKV, Vercel Edge Config. Distinct from first-party-db (a managed DATABASE service you provision and connect to) and from http-query-api (HTTP access to an external store) — edge-kv is colocated with the edge compute and read at the edge.

Not applicable

Developer access 4/9

Public APIDocumented programmatic API.

Supported

OpenAPI specMachine-readable OpenAPI / Swagger spec published.

Not supported

CLIOfficial command-line tool.

Supported

SDKOfficial client library/libraries.

Supported

SSH accessDirect SSH into workloads.

Not supported

Filesystem APIRemote file operations over the API (list/read/write/watch/copy/upload) without SSH.

Supported

Git deployDeploy from a Git repo / push-to-deploy.

Not supported

Private container registryHosted private image registry.

Not supported

E2B-compatible APIDrop-in compatibility with the E2B sandbox API/SDKs — existing E2B client code runs against this product by changing the endpoint/domain + key, with no business-code changes. E2B itself passes as the reference implementation. Distinct from public-api / sdk (the product has its own API — this key says it also speaks another vendor's) and from self-host-oss (a self-hosted E2B-compatible server is scored on both).

Not supported

HTTP data APIQuery / read / write the stored DATA over plain HTTP/REST (or GraphQL) WITHOUT the native protocol driver (Postgres wire / Redis RESP) — agent- and edge-friendly data access via fetch(). The DATA plane; distinct from public-api (a control-plane / management API). Auto-generated-from-schema REST/GraphQL (PostgREST, pg_graphql) is a flavour of this.

Not applicable

AI & agents 4/10

Built-in coding agentShips a first-party AI coding agent in the product.

Supported

Agent skillsInstallable / declarable agent skills or tools.

Supported

AI app builderPrompt-to-app / vibe-coding generation surface.

Not applicable

MCP serverExposes a Model Context Protocol server for agents.

Partially supported

MCP clientActs as an MCP client / consumes MCP tools.

Supported

MCP-server hostingRun/host MCP servers as a workload on the platform (distinct from exposing a first-party MCP control server — that is mcp-server).

Not supported

LLM gatewayRoutes LLM API calls through the platform (multi-provider).

Not supported

BYOK for LLMsBring-your-own LLM provider keys.

Not supported

Model inference API (first-party)A FIRST-PARTY hosted LLM/model inference API — the provider serves its OWN catalogue of (usually open-weight) models behind a (typically OpenAI-compatible) endpoint, billed per token. Distinct from llm-gateway (a multi-PROVIDER proxy/router for YOUR calls to external providers like OpenAI/Anthropic) and from byok-llm (bring your own provider keys) — here the platform IS the inference provider, serving its own models.

Not applicable

Autonomous QA agentA first-party AUTONOMOUS AI agent that QA-TESTS a running app / implementation — exercising it like a real user (clicking through flows, checking behaviour) and reporting bugs/defects (often back to a coding agent, or before a human review). Distinct from built-in-agent (a code-AUTHORING agent — this one VERIFIES the result, it does not write the feature; a product can ship both), from ai-guided-code-review (organises a diff for a HUMAN to review — not an autonomous tester), and from observability (runtime metrics/logs, not active testing).

Not supported

Credential-injection proxyThe platform holds real secrets OUTSIDE the workload and injects them on the wire (an egress / broker proxy swaps a placeholder or phantom token for the real credential on matching outbound requests), so code running in the sandbox — e.g. an untrusted agent — never sees or can exfiltrate the real key. Distinct from secrets-management (storage + injection INTO the workload as env vars/files — the workload holds the secret) and from egress-controls (outbound allow/deny POLICY; a product can have an allowlist without injecting credentials, and vice versa).

Supported

Preinstalled coding agentThe platform installs and launches a THIRD-PARTY coding agent (a harnesses.yml entry — Claude Code, Codex, OpenCode, Pi ...) inside a workspace/sandbox it provisions, with the agent's auth wired in (your own account or API key), so you start an agent session rather than an empty box. Distinct from built-in-agent (a FIRST-PARTY agent the vendor ships) and from harnesses[] (which records that a harness CAN target the product, not that the product runs it for you).

Not supported

Data 0/0

First-party databasePlatform-provided managed database.

Not applicable

Database branchingCopy-on-write branch of a DATABASE (schema + data) as a dev-lifecycle primitive — branch your data like code, usually instant via a metadata operation. Distinct from snapshots-forks (forks a running compute INSTANCE / VM state) and from preview-environments (a full per-PR environment that may USE a DB branch). For a data product a CoW branch maps HERE, not to snapshots-forks.

Not applicable

Vector searchFirst-class storage, indexing, and similarity search of vector embeddings — a native vector type/index or a managed vector DB. The data-layer primitive for RAG / semantic retrieval.

Not applicable

Ephemeral instant DB (no-signup)Provision a working, usable instance via a single command / HTTP call with NO account, signup, or card — typically time-boxed (expires unless claimed). A zero-onboarding path an agent can hit directly.

Not applicable

Platform & operations 2/3

Scheduled tasksCron / scheduled job primitive.

Supported

Durable workflowsDurable execution / long-running workflow primitive.

Partially supported

Preview environmentsA full EPHEMERAL environment spun up per PR / branch — compute + addons + (often) a DB branch — torn down on merge. More than preview-urls (which is just a shareable URL for one deploy).

Not applicable

Built-in observabilityFirst-party metrics / logs / tracing / APM / profiling included in the platform (no third-party stack required to see what a workload is doing).

Supported

Managed CI/CD runnersPlatform-hosted, drop-in CI/CD runner VMs (GitHub Actions / GitLab), typically faster and cheaper than the CI vendor's own hosted runners, billed per runner-minute; isolated + ephemeral per job. Distinct from git-deploy (push-to-deploy of an APP) and scheduled-tasks (cron) — this is managed CI COMPUTE you point your existing pipelines at.

Not applicable

Project template marketplaceA marketplace / gallery of prebuilt PROJECT STARTER templates (apps or websites) a user clones or launches a new project from and then customises — the "start from a template" surface of a builder / PaaS. Distinct from sandbox-templates (a COMPUTE base IMAGE you fork runtime INSTANCES from — Dockerfile / OCI), from app-builder (the prompt-to-app GENERATION surface — a product can have both), and from one-click OSS-app catalogues / helm-addon-marketplace (deploy a FINISHED app as-is, not a starter you build on).

Not applicable

Organisation & security 2/8

Built-in authPlatform-provided authentication / IAM for workloads.

Not applicable

SSO / SAMLEnterprise single sign-on.

Not supported

Secrets managementFirst-class secrets storage / injection.

Supported

TeamsMulti-user team accounts.

Supported

SharingShare a running workload/resource via link (optionally gated).

Not supported

BYOCRuns inside the customer's own cloud account.

Partially supported

Deploy into customers' VPCsA SaaS vendor uses the platform to deploy and operate ITS software inside ITS CUSTOMERS' cloud accounts / VPCs (nested or "customer BYOC"), managed from the vendor's control plane. Distinct from byoc (your own workloads in your own cloud account).

Not supported

Workload identityThe platform gives each workload its own verifiable identity (OIDC token, SPIFFE SVID, cloud IAM federation) that it exchanges for short-lived credentials, so no long-lived static secret is stored or injected. Distinct from secrets-management (stores / injects static secrets) and credential-injection-proxy (swaps real secrets in on the wire).

Not supported

Self-host / OSS coreOpen-source core that can be self-hosted.

Not supported

Proposed, not verified

Capabilities the scan saw but the registry does not track yet. A key is admitted only once two distinct products exhibit it. These are not scored.

Persistent cross-session agent memorypersistent-agent-memory
“Memory stores let the agent carry information across sessions: user preferences, project conventions, prior mistakes, and domain context.” platform.claude.com
Multiagent delegation and dynamic workflowsmulti-agent-orchestration
“Lets the agent hand work to other agents, as subagents or in dynamic workflows, and optionally consult an advisor model.” platform.claude.com
Outcome-driven iteration with independent graderoutcome-driven-agent-runs
“When you define an outcome, the harness automatically provisions a grader to evaluate the artifact against a rubric. The grader uses a separate context window to avoid being influenced by the main agent's implementation choices.” platform.claude.com
Between-session memory consolidation (research preview)between-session-memory-consolidation
“title: Dreams” platform.claude.com
Hard session spend ceilingsession-spend-budget
“A session budget is an optional hard spend ceiling you set when you create the session.” platform.claude.com

04 Agent readiness Pre-login surface · counts, not a grade

Can an agent read it?

parse-ability · docs, metadata, machine-readable surfaces

10/11

7 full · 3 partial · 91% of applicable checks

llms.txt
Supported
“https://platform.claude.com/llms.txt: substantive 82,905-byte documentation index, including Managed Agents and pricing.”
llms-full.txt
Supported
“https://platform.claude.com/llms-full.txt: 43,216,345 bytes HTTP 200; comprehensive index/content inspected, retained pointer per artifact cap.”
robots.txt AI policy
Partially supported
“https://platform.claude.com/robots.txt: User-Agent: *; Disallow: /api; no explicit AI-UA policy.”
JSON-LD
Not supported
“Subject HTML has no application/ld+json script; web-surface-signals.json records the observed head.”
Sitemap
Supported
“https://platform.claude.com/sitemap.xml: 372,340-byte XML urlset; pointer retains multiple entries.”
Meta tags
Supported
“Descriptive title/description, OG URL/image/title/description and Twitter cards on the Managed Agents overview.”
Markdown negotiation
Supported
“GET subject with Accept: text/markdown returned HTTP 200, Content-Type: text/markdown; charset=utf-8; .md alternate works.”
Content efficiency
Partially supported
“Subject HTML: 7550/334843 readable bytes = 2.25%; 1–5% ladder band.”
Docs discoverable
Supported
“https://claude.com/platform/api links directly to the Managed Agents overview and memory docs; header has Developer docs.”
Machine-readable pricing
Supported
“Pricing markdown has structured rate tables: session runtime $0.08/session-hour, tokens by model and worked examples.”
No anti-bot wall
Partially supported
“Public overview/docs/marketing fetched normally; favicon.svg returned 403 to plain fetch, recovered as actual SVG via sequential foxcrawl. Trust portal required JS rendering.”

Can an agent drive it?

act-ability · APIs, SDKs, MCP, credentials, webhooks

10/11

9 full · 1 partial · 91% of applicable checks

Public API
Supported
“Documented REST agents/sessions/environments/events/memory/workflows endpoints and beta client methods.”
OpenAPI spec
Not supported
“API intro/auth provides navigable references, not a downloadable spec link. /openapi.json, /docs/openapi.json and /swagger.json on platform plus /openapi.json and /v1/openapi.json on api.anthropic.com returned 404.”
MCP server
Supported
“https://platform.claude.com/docs/mcp documented via valid server-card JSON: search/read docs MCP. Not an agent control-plane server.”
SDK packages
Supported
“Official client SDKs in Python, TypeScript, C#, Go, Java, PHP and Ruby with Managed Agents beta methods.”
Auth documented
Supported
“API-key/Bearer/workspace scope docs, OAuth token exchange via Workload Identity Federation; environment-scoped worker keys and per-session secrets documented separately.”
Self-serve credentials
Supported
“Workload Identity Federation documents POST /v1/oauth/token for programmatic short-lived Claude API tokens; service account/issuer/rule setup prerequisite. API-key creation itself remains a Console step; no signup attempt.”
Webhooks
Supported
“Managed Agents webhook guide documents endpoint registration, session event types and signature verification.”
CLI tool
Supported
“Official ant CLI, anthropics/anthropic-cli; beta:sessions create and worker start documented.”
Error model
Supported
“API errors document JSON type:error, nested error type/message and request_id, with HTTP error classes.”
Rate limits documented
Supported
“Managed Agents reference: 300 create/minute, 1,200 read/minute per organization; shared API rate-limit headers documented.”
Agent config files
Partially supported
“Public managed-agent skills guide/libraries expose a skills listing surface; /AGENTS.md and /.well-known/agent returned HTTP 404. No multiple agent-instruction discovery surfaces established.”

05 Coding harnesses Which agents and IDEs are documented to run here

Advertised integrations 0

The public surface names no coding harness as supported or documented-to-run-here.

Plausible compatibility 0

Derived, not stored: the product passes SSH access, so any CLI coding agent is installable inside it. This is plausible compatibility, not a supported integration.

No general shell access documented, so nothing is derived. Absence is not unsupported.

06 Compliance & regions Standards held, with ordinal rigor; never a score

Certifications held 3

ISO/IEC 27001
certifiedhostedRendered matrix covers Claude via Anthropic's API, not an explicit Managed Agents service-specific report. No claim for customer self-hosted worker infrastructure.
“Claude via Anthropic's API | ISO 27001 ✅”
Source trust.anthropic.comConfidence: medium
SOC 2 Type II
certifiedhostedRendered matrix covers Claude via Anthropic's API, not an explicit Managed Agents service-specific report. No claim for customer self-hosted worker infrastructure.
“Claude via Anthropic's API | SOC 2 Type 2 ✅”
Source trust.anthropic.comConfidence: medium
CSA STAR
self-attestedhostedRendered matrix covers Claude via Anthropic's API, not an explicit Managed Agents service-specific report. No claim for customer self-hosted worker infrastructure.
“Claude via Anthropic's API | CSA Star ✅”
Source trust.anthropic.comConfidence: medium

Rendered trust center public matrix observed. API-wide attestations above are medium-confidence scope, not gated service-specific reports. Managed Agents overview explicitly says NOT eligible for Zero Data Retention or HIPAA BAA: the broader API HIPAA checkmark MUST NOT be inherited. ISO 42001 and NIST 800-171 appear in vendor table but are outside current compliance registry; kept here without admitting keys. FedRAMP/DoD apply only to other deployment SKUs, not this service.

Regions —

Regions are not disclosed on the public surface.

Model inference geography supports global/US routing; sandbox/session storage regions or a regional availability map are not disclosed. Do not infer service regions from model routing or AWS sibling distribution.

Legal

Privacy notice Terms of service

07 Company & presence Facts only, not scored

Company

Headquarters: Not disclosed
Founded: —
Team size: Not disclosed
Hiring: Hiring: careers page invites applicants and links Explore open roles.

Activity

Last release: — platform.claude.com
Last blog post: 2026-10-08 — Building effective agent automations, a scheduled Claude Managed Agents walkthrough. claude.com

Presence 11

Links found on the public surface scanned; not an exhaustive search.

08 Sources & method How this entry was produced

Public surface only

Everything here was read from platform.claude.com's unauthenticated pages, docs, pricing and repository on 12 Oct 2026. Nothing behind a login was used.

Statuses, not scores

Capabilities are pass, partial or fail against a written rubric (features v21). “Not assessed” means the scan predates the key.

Confidence is separate

Each fact carries its own confidence. Low-confidence facts are shown, never hidden, so you can weigh them.

Schema: scan v5
Features registry: v21
Keys tracked today: 61
Assessed on this entry: 61

Something wrong on this page?

Nearby in the atlas

All Workflow engine products →