694 pages for agents.
Titles and paths first, then pages whose text carries it. Each row opens that page as this site last read it.
before_id is the first_id from a previous response
Claude Developer Platform · in the page
manage-claude/compliance-integration-patterns
…ce-sessions"> List the sessions your users run in Claude apps and agents, such as Cowork and Claude Code, and retrieve their transcripts. </Card> </CardGroup>
compliance-sessions
Claude Developer Platform · in the page
manage-claude/compliance-sessions
…ions description: List the sessions your users run in Claude apps and agents, such as Claude Cowork and Claude Code, and retrieve their transcripts through the Compliance API. --- <Note> The endpoi…
data-residency
Claude Developer Platform · in the page
manage-claude/data-residency
…ude Console](https://platform.claude.com/). <Note> [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) supports geographic pinning at the agent level: `inference_ge…
opentelemetry
Claude Developer Platform · in the page
manage-claude/opentelemetry
…description: Trace your Messages API requests, tool uses, and Managed Agents sessions with OpenTelemetry spans from the Claude SDK and the Claude API. featureMetadata: topic: title: OpenTelemetr…
api
Claude Developer Platform · in the page
manage-claude/opentelemetry/api
…o send OpenTelemetry traces of your Messages API requests and Managed Agents sessions to your observability platform. featureMetadata: topic: title: OpenTelemetry url: https://platform.claud…
sdk
Claude Developer Platform · in the page
manage-claude/opentelemetry/sdk
…ws: - label: Works with value: Messages API, Claude Managed Agents --- With OpenTelemetry, the Claude SDK can emit a span for each request that it sends and each tool use that the [tool run…
plugins-api
Claude Developer Platform · in the page
manage-claude/plugins-api
…es tools (for example, a plugin that holds only skills, commands, and agents, none with `allowed-tools`).…
rate-limits-api
Claude Developer Platform · in the page
manage-claude/rate-limits-api
…porting resources. Limits for other products, such as [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), are not included. ### Key concepts * **Rate limit groups:*…
wif-reference
Claude Developer Platform · in the page
manage-claude/wif-reference
…odels](https://platform.claude.com/docs/en/api/models/list), [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) and their sessions, [Files](https://platform.claude.com/docs/…
workload-identity-federation
Claude Developer Platform · in the page
manage-claude/workload-identity-federation
…w; for example, the [MCP tunnels](https://platform.claude.com/docs/en/agents-and-tools/mcp-tunnels/overview) create-tunnel modal creates rules scoped to `workspace:manage_tunnels`. See [OAuth scopes](…
workspaces
Claude Developer Platform · in the page
manage-claude/workspaces
…d differently: * **[MCP tunnels](https://platform.claude.com/docs/en/agents-and-tools/mcp-tunnels/overview)** are managed with a `workspace:manage_tunnels` OAuth token obtained through [Workload Iden…
Or, for Claude Mythos 5.1, which offers the same capabilities to verified organizations:
Claude Developer Platform · in the page
models/fable-5-1/migration-guide
…d-with-claude/working-with-messages) code. If you use [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), no changes beyond updating the model name are required. </No…
whats-new-fable-5-1
Claude Developer Platform · in the page
models/fable-5-1/whats-new-fable-5-1
…ict: true` with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use), or move the schema to [structured outputs](https://platform.claude.com/docs/en/build-w…
migration-guide
Claude Developer Platform · in the page
models/haiku-5-5/migration-guide
…d-with-claude/working-with-messages) code. If you use [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), no changes beyond updating the model name are required. </No…
whats-new-haiku-5-5
Claude Developer Platform · in the page
models/haiku-5-5/whats-new-haiku-5-5
…-pricing). | | [Browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool)…
migration-guide
Claude Developer Platform · in the page
models/opus-5-5/migration-guide
…d-with-claude/working-with-messages) code. If you use [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), no changes beyond updating the model name are required. </No…
whats-new-opus-5-5
Claude Developer Platform · in the page
models/opus-5-5/whats-new-opus-5-5
…ict: true` with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use), or move the schema to [structured outputs](https://platform.claude.com/docs/en/build-w…
Models overview
Claude Developer Platform · in the page
models/overview
…he model accepts the [web search](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool) and [code execution](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code…
migration-guide
Claude Developer Platform · in the page
models/sonnet-5-5/migration-guide
…d-with-claude/working-with-messages) code. If you use [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), no changes beyond updating the model name are required. </No…
whats-new-sonnet-5-5
Claude Developer Platform · in the page
models/sonnet-5-5/whats-new-sonnet-5-5
…ict: true` with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use), or move the schema to [structured outputs](https://platform.claude.com/docs/en/build-w…
overview
Claude Developer Platform · in the page
release-notes/overview
…cludes the web fetch tool fails with a 400 error. In a Claude Managed Agents session, `web_fetch` calls return an error result to the agent instead. With web fetch on, admins can also set allowed or b…
mitigate-jailbreaks
Claude Developer Platform · in the page
test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks
…epticism. See [Handle tool calls](https://platform.claude.com/docs/en/agents-and-tools/tool-use/handle-tool-calls) for the `tool_result` format. * **Tell Claude what the content is and where it came…
Set up Claude Code for your organization
Claude Code CLI · in the page
admin-setup
…can add and install from, reject the CLI flags that sideload plugins, agents, and MCP servers for a single run, block [`command` plugin sources](/docs/en/plugins/marketplace-reference#command-plugin-s…
Escalate hard decisions with the advisor tool
Claude Code CLI · in the page
advisor
…infrastructure as a [server tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool), available to both subscription and API-billed accounts. You choose which model acts as th…
How the agent loop works
Claude Code CLI · in the page
agent-sdk/agent-loop
…tool execution, context window, and architecture that power your SDK agents. The Agent SDK lets you embed Claude Code's autonomous agent loop in your own applications. The SDK is a standalone packag…
Use Claude Code features in the SDK
Claude Code CLI · in the page
agent-sdk/claude-code-features
…ructions, skills, hooks, and other Claude Code features into your SDK agents. The Agent SDK is built on the same foundation as Claude Code, which means your SDK agents have access to the same filesys…
Configure your agent
Claude Code CLI · in the page
agent-sdk/configuration
…to pin a specific model, or to pick a smaller one for faster, cheaper agents. The value takes a model alias or a full model name; aliases and the versions they resolve to are listed under [Model alias…
Track cost and usage
Claude Code CLI · in the page
agent-sdk/cost-tracking
…rs only that turn, and within it only the main agent loop, not any subagents it ran. * **`total_cost_usd` and `modelUsage`, or `model_usage` in Python**: carry the running total for the whole call so…
Examples
Claude Code CLI · in the page
agent-sdk/examples
…s://platform.claude.com/docs/en/about-claude/use-case-guides/commerce-agents). ## Work through a Python recipe The Claude Cookbook's Agent SDK series is a sequence of recipes, each a Python notebook…
Rewind file changes with checkpointing
Claude Code CLI · in the page
agent-sdk/file-checkpointing
…that file in the main conversation. [Subagent](/docs/en/agent-sdk/subagents.md) edits aren't tracked, while edits from a [skill with `context: fork`](/docs/en/skills#run-skills-in-a-subagent) running…
Intercept and control agent behavior with hooks
Claude Code CLI · in the page
agent-sdk/hooks
…error instead of a normal stop | Log failures or send alerts | | `SubagentStart` | Yes | Yes | Subagent initialization | Track parallel task spawning | | `SubagentStop` | Yes | Yes | Subagent complet…
Hosting the Agent SDK
Claude Code CLI · in the page
agent-sdk/hosting
…n the agent loop itself on your own infrastructure, consider [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) instead. Anthropic hosts the agent loop, and your application…
Connect to external tools with MCP
Claude Code CLI · in the page
agent-sdk/mcp
….io/docs/getting-started/intro) is an open standard for connecting AI agents to external tools and data sources. With MCP, your agent can query databases, integrate with APIs like Slack and GitHub, an…
Migrate to Claude Agent SDK
Claude Code CLI · in the page
agent-sdk/migration-guide
…. This change reflects the SDK's broader capabilities for building AI agents beyond coding tasks. Migrating from the OpenAI Agents SDK instead? The [OpenAI Agents SDK migration recipe](https://platfo…
Modifying system prompts
Claude Code CLI · in the page
agent-sdk/modifying-system-prompts
…where a human watches and steers the work. Write your own prompt for agents with a different surface, identity, or permission model. ## How system prompts work A system prompt is the initial instru…
Observability with OpenTelemetry
Claude Code CLI · in the page
agent-sdk/observability
…SDK to your observability backend using OpenTelemetry. When you run agents in production, you need visibility into what they did: * which tools they called * how long each model request took * how…
Agent SDK overview
Claude Code CLI · in the page
agent-sdk/overview
# Agent SDK overview > Build production AI agents with Claude Code as a library An agent is an application that completes a task by planning its own steps and calling tools that read files, run comm…
Configure permissions
Claude Code CLI · in the page
agent-sdk/permissions
…es still go to your `canUseTool` callback. Plan mode holds for the subagents you define too, so that handing work to one doesn't get around reviewing the plan first. > > The subagent inherits `plan`,…
Plugins in the SDK
Claude Code CLI · in the page
agent-sdk/plugins
…in the SDK > Load custom plugins to extend Claude Code with skills, agents, hooks, and MCP servers through the Agent SDK Plugins let you extend Claude Code with custom functionality that can be sha…
Agent SDK reference - Python
Claude Code CLI · in the page
agent-sdk/python
…| `str \| None` | For messages from a [nested subagent](/docs/en/sub-agents.md#let-subagents-spawn-their-own-subagents), the agent id of the parent subagent. `None` for main-session messages, top-lev…
Quickstart
Claude Code CLI · in the page
agent-sdk/quickstart
…rt > Get started with the Python or TypeScript Agent SDK to build AI agents that work autonomously Use the Agent SDK to build an AI agent that reads your code, finds bugs, and fixes them, all withou…
Persist sessions to external storage
Claude Code CLI · in the page
agent-sdk/session-storage
…an opaque key suffix; it follows the on-disk layout, for example `subagents/agent-<id>`. When `subpath` is undefined the key refers to the main transcript. | Method | Required | Called when | | :- |…
Stream responses in real-time
Claude Code CLI · in the page
agent-sdk/streaming-output
…time). For input modes (how you send messages), see [Send messages to agents](/docs/en/agent-sdk/streaming-vs-single-mode.md). You can also [stream responses using the Agent SDK via the CLI](/docs/en/…
Streaming Input
Claude Code CLI · in the page
agent-sdk/streaming-vs-single-mode
…aude Agent SDK supports two distinct input modes for interacting with agents: * **Streaming Input Mode**: a persistent, interactive session * **Single Message Input**: one-shot queries that use sessi…
Track todos
Claude Code CLI · in the page
agent-sdk/todo-tracking
…ng them, report background tasks such as backgrounded commands and subagents. In the message stream, you see todo activity as `tool_use` blocks in the assistant messages. ### Monitor todo changes Th…
Scale to many tools with tool search
Claude Code CLI · in the page
agent-sdk/tool-search
…ism, see [Tool search in the API](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-search-tool). > [!NOTE] > > Tool search isn't supported on Microsoft Foundry [deployments hosted o…
Troubleshoot the Agent SDK
Claude Code CLI · in the page
agent-sdk/troubleshooting
…agent-sdk/plugins.md#troubleshooting) | | Claude not delegating to subagents, filesystem-based agents not loading | [Subagents troubleshooting](/docs/en/agent-sdk/subagents.md#troubleshooting) | | Che…
Agent SDK reference - TypeScript
Claude Code CLI · in the page
agent-sdk/typescript
…`string \| null` | For messages from a [nested subagent](/docs/en/sub-agents.md#let-subagents-spawn-their-own-subagents), the `agentId` of the subagent that spawned it. `null` for main-session message…
Handle approvals and user input
Claude Code CLI · in the page
agent-sdk/user-input
…nsole.log(message.result); } } main(); ``` ## Limitations * **Subagents**: `AskUserQuestion` is not currently available in subagents spawned via the Agent tool * **Question limits**: each `AskUse…
Orchestrate teams of Claude Code sessions
Claude Code CLI · in the page
agent-teams
…e you set up a team, check whether a lighter option does the job. [Subagents](/docs/en/sub-agents.md) work within a single session, and with [cross-session messaging](/docs/en/cross-session-messaging.…