feat: bump cookbook version

Author: junhsss

content/docs/cookbook/agentkit.mdx

@@ -3,7 +3,7 @@ title: Build a browser agent with Inngest AgentKit
 description: "Integrate Steel with Inngest's AgentKit framework."
 ---
 
-<RecipeMeta href="https://github.com/steel-dev/steel-cookbook/tree/3312a27bde50b050c163b3a379f6b7c4219834a3/examples/agentkit" path="examples/agentkit" authors={[{"handle":"junhsss","name":"Jun Ryu","avatar":"https://github.com/junhsss.png?size=40"}]} updated="2026-04-24" />
+<RecipeMeta href="https://github.com/steel-dev/steel-cookbook/tree/7ac7c6f07cfc564a4f3d41fd79abbbb8837b820c/examples/agentkit" path="examples/agentkit" authors={[{"handle":"junhsss","name":"Jun Ryu","avatar":"https://github.com/junhsss.png?size=40"}]} updated="2026-04-24" />
 
 Agent Kit is Inngest's framework for multi-agent systems: a **tool** is a typed function the model can call, an **agent** bundles a system prompt with a tool set, and a **network** groups agents so they can collaborate on a task. Agent Kit handles the routing between them and wraps each call in Inngest's `step.run` checkpoint, so a network that crashes mid-flight resumes from the last finished step instead of starting over.
 
@@ -124,7 +124,7 @@ A run lands in the ~20-40 second range. Steel session startup dominates; the `gp
 ## Related recipes
 
 <RecipeGrid>
+<RecipeCard slug="claude-agent-sdk" title={"Build a browser agent with the Claude Agent SDK"} description={"Use Steel with the Claude Agent SDK (TypeScript) to build a tool-using browser agent on Anthropic's first-party agent loop."} topics={['Agents']} date="2026-04-29" />
 <RecipeCard slug="openai-agents" title={"Build a typed browser agent with the OpenAI Agents SDK"} description={"Use Steel with the OpenAI Agents SDK for TypeScript to build typed, tool-using browser agents."} topics={['Agents', 'Typed output']} date="2026-04-23" />
 <RecipeCard slug="vercel-ai-sdk" title={"Build a typed browser agent with the Vercel AI SDK"} description={"Use Steel with the Vercel AI SDK v6 ToolLoopAgent for typed, tool-using browser agents."} topics={['Agents', 'Typed output']} date="2026-04-23" />
-<RecipeCard slug="vercel-ai-sdk-nextjs" title={"Stream a browser agent into a Next.js chat app"} description={"A Next.js App Router chat app where a Vercel AI SDK agent drives a Steel cloud browser with embedded Live View."} topics={['Agents', 'Typed output', 'Next.js']} date="2026-04-23" />
 </RecipeGrid>

content/docs/cookbook/agno.mdx

@@ -3,7 +3,7 @@ title: Build a browser agent with Agno
 description: Integrate Steel with the Agno agent framework.
 ---
 
-<RecipeMeta href="https://github.com/steel-dev/steel-cookbook/tree/3312a27bde50b050c163b3a379f6b7c4219834a3/examples/agno" path="examples/agno" authors={[{"handle":"junhsss","name":"Jun Ryu","avatar":"https://github.com/junhsss.png?size=40"}]} updated="2026-04-24" />
+<RecipeMeta href="https://github.com/steel-dev/steel-cookbook/tree/7ac7c6f07cfc564a4f3d41fd79abbbb8837b820c/examples/agno" path="examples/agno" authors={[{"handle":"junhsss","name":"Jun Ryu","avatar":"https://github.com/junhsss.png?size=40"}]} updated="2026-04-24" />
 
 Agno's primitive is `Agent(model=..., tools=[...])`. Tools are typed Python methods grouped into a `Toolkit` subclass; docstrings and type hints become the JSON schema the model sees. No manual function-calling boilerplate, no separate tool-registration step.
 
@@ -131,7 +131,7 @@ finally:
 ## Related recipes
 
 <RecipeGrid>
+<RecipeCard slug="claude-agent-sdk" title={"Build a browser agent with the Claude Agent SDK"} description={"Use Steel with the Claude Agent SDK (TypeScript) to build a tool-using browser agent on Anthropic's first-party agent loop."} topics={['Agents']} date="2026-04-29" />
 <RecipeCard slug="openai-agents" title={"Build a typed browser agent with the OpenAI Agents SDK"} description={"Use Steel with the OpenAI Agents SDK for TypeScript to build typed, tool-using browser agents."} topics={['Agents', 'Typed output']} date="2026-04-23" />
 <RecipeCard slug="vercel-ai-sdk" title={"Build a typed browser agent with the Vercel AI SDK"} description={"Use Steel with the Vercel AI SDK v6 ToolLoopAgent for typed, tool-using browser agents."} topics={['Agents', 'Typed output']} date="2026-04-23" />
-<RecipeCard slug="vercel-ai-sdk-nextjs" title={"Stream a browser agent into a Next.js chat app"} description={"A Next.js App Router chat app where a Vercel AI SDK agent drives a Steel cloud browser with embedded Live View."} topics={['Agents', 'Typed output', 'Next.js']} date="2026-04-23" />
 </RecipeGrid>

content/docs/cookbook/auth-context.mdx

@@ -3,7 +3,7 @@ title: Reuse authenticated sessions across browsers
 description: Maintain authenticated sessions across Steel browser instances by capturing and reusing cookies and local storage.
 ---
 
-<RecipeMeta href="https://github.com/steel-dev/steel-cookbook/tree/3312a27bde50b050c163b3a379f6b7c4219834a3/examples/auth-context" path="examples/auth-context" authors={[{"handle":"junhsss","name":"Jun Ryu","avatar":"https://github.com/junhsss.png?size=40"}]} updated="2026-04-24" />
+<RecipeMeta href="https://github.com/steel-dev/steel-cookbook/tree/7ac7c6f07cfc564a4f3d41fd79abbbb8837b820c/examples/auth-context" path="examples/auth-context" authors={[{"handle":"junhsss","name":"Jun Ryu","avatar":"https://github.com/junhsss.png?size=40"}]} updated="2026-04-24" />
 
 An auth context is a snapshot of a browser's cookies and local storage at a point in time. Steel exposes one endpoint to read it and one session option to restore it:
 

content/docs/cookbook/browser-use-captcha-auto.mdx

@@ -3,7 +3,7 @@ title: Solve CAPTCHAs automatically in a Browser Use agent
 description: Build an AI agent with browser-use and Steel that solves CAPTCHAs automatically.
 ---
 
-<RecipeMeta href="https://github.com/steel-dev/steel-cookbook/tree/3312a27bde50b050c163b3a379f6b7c4219834a3/examples/browser-use-captcha-auto" path="examples/browser-use-captcha-auto" authors={[{"handle":"jagadeshjai","name":"Jagadesh Jai","avatar":"https://github.com/jagadeshjai.png?size=40"}]} updated="2026-04-24" />
+<RecipeMeta href="https://github.com/steel-dev/steel-cookbook/tree/7ac7c6f07cfc564a4f3d41fd79abbbb8837b820c/examples/browser-use-captcha-auto" path="examples/browser-use-captcha-auto" authors={[{"handle":"jagadeshjai","name":"Jagadesh Jai","avatar":"https://github.com/jagadeshjai.png?size=40"}]} updated="2026-04-24" />
 
 Steel can solve CAPTCHAs inside a session without the agent lifting a finger. This recipe wires that into Browser Use: one flag at session creation, one custom tool the agent calls to block until the solver reports done. Everything else is the same perception-plan-act loop as the base [Browser Use](/cookbook/browser-use) recipe.
 
@@ -97,5 +97,5 @@ A run usually finishes in under a minute: a few cents of Steel session time plus
 <RecipeGrid>
 <RecipeCard slug="browser-use-captcha-manual" title={"Solve reCAPTCHA v2 manually with Browser Use"} description={"Manually solve reCAPTCHA v2 using Steel's CAPTCHA API with the browser-use framework."} topics={['Agents', 'Browser Use', 'Captchas']} date="2026-02-10" />
 <RecipeCard slug="browser-use" title={"Build a browser agent with Browser Use"} description={"Integrate Steel with the browser-use framework for AI-driven web automation."} topics={['Agents', 'Browser Use']} date="2025-02-20" />
-<RecipeCard slug="openai-agents" title={"Build a typed browser agent with the OpenAI Agents SDK"} description={"Use Steel with the OpenAI Agents SDK for TypeScript to build typed, tool-using browser agents."} topics={['Agents', 'Typed output']} date="2026-04-23" />
+<RecipeCard slug="claude-agent-sdk" title={"Build a browser agent with the Claude Agent SDK"} description={"Use Steel with the Claude Agent SDK (TypeScript) to build a tool-using browser agent on Anthropic's first-party agent loop."} topics={['Agents']} date="2026-04-29" />
 </RecipeGrid>

content/docs/cookbook/browser-use-captcha-manual.mdx

@@ -3,7 +3,7 @@ title: Solve reCAPTCHA v2 manually with Browser Use
 description: "Manually solve reCAPTCHA v2 using Steel's CAPTCHA API with the browser-use framework."
 ---
 
-<RecipeMeta href="https://github.com/steel-dev/steel-cookbook/tree/3312a27bde50b050c163b3a379f6b7c4219834a3/examples/browser-use-captcha-manual" path="examples/browser-use-captcha-manual" authors={[{"handle":"jagadeshjai","name":"Jagadesh Jai","avatar":"https://github.com/jagadeshjai.png?size=40"}]} updated="2026-04-24" />
+<RecipeMeta href="https://github.com/steel-dev/steel-cookbook/tree/7ac7c6f07cfc564a4f3d41fd79abbbb8837b820c/examples/browser-use-captcha-manual" path="examples/browser-use-captcha-manual" authors={[{"handle":"jagadeshjai","name":"Jagadesh Jai","avatar":"https://github.com/jagadeshjai.png?size=40"}]} updated="2026-04-24" />
 
 Steel can solve CAPTCHAs for you in the background, or it can hand you the status API and let you drive. This recipe picks the second path. The session is created with auto-solving explicitly off, a custom Browser Use tool polls `client.sessions.captchas.status()`, and it calls `client.sessions.captchas.solve()` only for the CAPTCHA type you care about. Every state transition (detected, solving, validating, solved) is yours to read and react to.
 
@@ -135,5 +135,5 @@ A run takes ~60 seconds and costs Steel session time plus OpenAI tokens for each
 <RecipeGrid>
 <RecipeCard slug="browser-use-captcha-auto" title={"Solve CAPTCHAs automatically in a Browser Use agent"} description={"Build an AI agent with browser-use and Steel that solves CAPTCHAs automatically."} topics={['Agents', 'Browser Use', 'Captchas']} date="2025-02-20" />
 <RecipeCard slug="browser-use" title={"Build a browser agent with Browser Use"} description={"Integrate Steel with the browser-use framework for AI-driven web automation."} topics={['Agents', 'Browser Use']} date="2025-02-20" />
-<RecipeCard slug="openai-agents" title={"Build a typed browser agent with the OpenAI Agents SDK"} description={"Use Steel with the OpenAI Agents SDK for TypeScript to build typed, tool-using browser agents."} topics={['Agents', 'Typed output']} date="2026-04-23" />
+<RecipeCard slug="claude-agent-sdk" title={"Build a browser agent with the Claude Agent SDK"} description={"Use Steel with the Claude Agent SDK (TypeScript) to build a tool-using browser agent on Anthropic's first-party agent loop."} topics={['Agents']} date="2026-04-29" />
 </RecipeGrid>

content/docs/cookbook/browser-use.mdx

@@ -3,7 +3,7 @@ title: Build a browser agent with Browser Use
 description: Integrate Steel with the browser-use framework for AI-driven web automation.
 ---
 
-<RecipeMeta href="https://github.com/steel-dev/steel-cookbook/tree/3312a27bde50b050c163b3a379f6b7c4219834a3/examples/browser-use" path="examples/browser-use" authors={[{"handle":"junhsss","name":"Jun Ryu","avatar":"https://github.com/junhsss.png?size=40"}]} updated="2026-04-24" />
+<RecipeMeta href="https://github.com/steel-dev/steel-cookbook/tree/7ac7c6f07cfc564a4f3d41fd79abbbb8837b820c/examples/browser-use" path="examples/browser-use" authors={[{"handle":"junhsss","name":"Jun Ryu","avatar":"https://github.com/junhsss.png?size=40"}]} updated="2026-04-24" />
 
 Browser Use is an agent framework: you give it an LLM, a browser, and a natural-language `task`, and it runs a perception-plan-act loop until the task is done. It doesn't need selectors or scripted steps. The model reads the page, decides the next action, and executes it against the browser you give it. The browser in this recipe is a Steel session, so the agent runs on managed cloud Chrome with stealth, proxies, and a live viewer instead of local Chromium.
 
@@ -72,5 +72,5 @@ A run costs a few cents of Steel session time plus OpenAI tokens for each step t
 <RecipeGrid>
 <RecipeCard slug="browser-use-captcha-manual" title={"Solve reCAPTCHA v2 manually with Browser Use"} description={"Manually solve reCAPTCHA v2 using Steel's CAPTCHA API with the browser-use framework."} topics={['Agents', 'Browser Use', 'Captchas']} date="2026-02-10" />
 <RecipeCard slug="browser-use-captcha-auto" title={"Solve CAPTCHAs automatically in a Browser Use agent"} description={"Build an AI agent with browser-use and Steel that solves CAPTCHAs automatically."} topics={['Agents', 'Browser Use', 'Captchas']} date="2025-02-20" />
-<RecipeCard slug="openai-agents" title={"Build a typed browser agent with the OpenAI Agents SDK"} description={"Use Steel with the OpenAI Agents SDK for TypeScript to build typed, tool-using browser agents."} topics={['Agents', 'Typed output']} date="2026-04-23" />
+<RecipeCard slug="claude-agent-sdk" title={"Build a browser agent with the Claude Agent SDK"} description={"Use Steel with the Claude Agent SDK (TypeScript) to build a tool-using browser agent on Anthropic's first-party agent loop."} topics={['Agents']} date="2026-04-29" />
 </RecipeGrid>