more

elithrar · elithrar · commit 32aa34252c30 · 2025-03-17T08:25:37.000-04:00
diff --git a/src/assets/images/agents/agents-apng.apng b/src/assets/images/agents/agents-apng.apng
diff --git a/src/content/changelog/agents/2025-02-25-agents-sdk.mdx b/src/content/changelog/agents/2025-02-25-agents-sdk.mdx
@@ -9,23 +9,23 @@ date: 2025-02-25T14:00:00Z
 
 We've released the [agents-sdk](http://blog.cloudflare.com/build-ai-agents-on-cloudflare/), a package and set of tools that help you build and ship AI Agents.
 
-You can get up and running with a [chat-based AI Agent](https://github.com/cloudflare/agents-starter) (and deploy it to Workers) that uses the `agents-sdk`, tool calling, and state syncing with a React-based front-end by running the following command:
+You can get up and running with a [chat-based AI Agent](https://github.com/cloudflare/agents-starter) (and deploy it to Workers) that uses the Agents SDK, tool calling, and state syncing with a React-based front-end by running the following command:
 
 ```sh
 npm create cloudflare@latest agents-starter -- --template="cloudflare/agents-starter"
 # open up README.md and follow the instructions
 ```
 
-You can also add an Agent to any existing Workers application by installing the `agents-sdk` package directly
+You can also add an Agent to any existing Workers application by installing the `agents` package directly
 
 ```sh
-npm i agents-sdk
+npm i agents
 ```
 
 ... and then define your first Agent:
 
 ```ts
-import { Agent } from 'agents-sdk';
+import { Agent } from 'agents';
 
 export class YourAgent extends Agent<Env> {
 	// Build it out
@@ -37,4 +37,4 @@ export class YourAgent extends Agent<Env> {
 }
 ```
 
-Head over to the [Agents documentation](/agents/) to learn more about the `agents-sdk`, the SDK APIs, as well as how to test and deploying agents to production.
+Head over to the [Agents documentation](/agents/) to learn more about the Agents SDK, the SDK APIs, as well as how to test and deploying agents to production.
diff --git a/src/content/changelog/agents/2025-03-17-npm-i-agents.mdx b/src/content/changelog/agents/2025-03-17-npm-i-agents.mdx
@@ -0,0 +1,70 @@
+---
+title: npm i agents
+description: Install the latest version of the `agents` SDK to build multi-agent applications, use the new RPC API, and visit the latest documentation updates.
+products:
+  - agents
+  - workers
+date: 2025-03-17T14:00:00Z
+---
+
+![npm i agents](~/assets/images/agents/npm-i-agents.apng)
+
+#### Multi-Agent applications and RPC
+
+We've added a number of big new features to the Agents SDK over the past few weeks, including:
+
+- TODO
+- TODO
+- TODO: the regular client now syncs state on the agent (just like the react version)
+- TODO: useAgentChat bug fixes for passing headers/credentials, properly clearing cache on unmount, etc
+- TODO: experiemental /schedule module with a prompt/schema for adding scheduling to your app (with evals!)
+
+We've also fixed a nubmer of bugs with state synchronization and the React hooks.
+
+### Call Agent methods from your client code
+
+We've added a new [`@callable` decorator](/agents/api-reference/client-api/) for defining methods that can be called directly from clients. This allows you call methods from within your client code: you can call methods (with arguments) and get native JavaScript objects back.
+
+<TypeScriptExample>
+
+```ts
+
+```
+
+</TypeScriptExample>
+
+#### agents-starter
+
+TODO
+
+- TODO
+- Upgraded to use the latest [wrangler v4](/changelog/2025-03-13-wrangler-v4/) release.
+- [Workers AI](/workers-ai/) is now the default AI provider in the [`agents-starter`](https://github.com/cloudflare/agents-starter) project: this uses the new [structured outputs](/changelog/2025-02-25-json-mode/) (or "JSON mode") support now in Workers AI and the [`workers-ai-provider`](https://sdk.vercel.ai/providers/community-providers/cloudflare-workers-ai#generateobject).
+
+#### More documentation
+
+We've contined to build out the Agents SDK documentation, including:
+
+- Expanded [API reference documentation](/agents/api-reference/), covering the methods and properties exposed by the Agents SDK, as well as more usage examples.
+- A new [Client API](/agents/api-reference/client-api/) reference that documents `useAgent`, `useAgentChat` and the new `@callable` decorator exposed by the SDK.
+- New documentation on how to [call agents](/agents/api-refererence/calling-agents/) and authenticate clients, using [Server-Sent Events (SSE)](/agents/api-refererence/http-sse/).
+
+#### `agents-sdk` -> `agents`
+
+We've also renamed the Agents package to just `agents` (it's cleaner). If you've already been building with the Agents SDK, you can update your dependencies to use the new package name:
+
+```sh
+# Remove the old (deprecated) package
+npm uninstall agents-sdk
+
+# Install the new package
+npm i agents
+
+# Find instances of the old package name in your codebase
+grep -r 'agents-sdk' .
+# Replace instances of the old package name with the new one
+# (or use find-replace in your editor)
+sed -i 's/agents-sdk/agents/g' $(grep -rl 'agents-sdk' .)
+```
+
+If you're still wondering what Agents are, [read our blog on building AI Agents on Cloudflare](https://blog.cloudflare.com/build-ai-agents-on-cloudflare/) and/or visit the [Agents documentation](/agents/) to learn more.
diff --git a/src/content/docs/agents/api-reference/agents-api.mdx b/src/content/docs/agents/api-reference/agents-api.mdx
@@ -8,14 +8,14 @@ sidebar:
 
 import { MetaInfo, Render, Type, TypeScriptExample, WranglerConfig } from "~/components";
 
-This page provides an overview of the Agent SDK API, including the `Agent` class, methods and properties built-in to the `agents-sdk`.
+This page provides an overview of the Agent SDK API, including the `Agent` class, methods and properties built-in to the Agents SDK.
 
-An Agent is a JavaScript class that extends the `Agent` class from the `agents-sdk` package. An Agent encapsulates all of the logic for an Agent, including how clients can connect to it, how it stores state, the methods it exposes, and any error handling.
+An Agent is a JavaScript class that extends the `Agent` class from the Agents SDK package. An Agent encapsulates all of the logic for an Agent, including how clients can connect to it, how it stores state, the methods it exposes, and any error handling.
 
 <TypeScriptExample>
 
 ```ts
-import { Agent } from "agents-sdk";
+import { Agent } from "agents";
 
 class MyAgent extends Agent {
 	// Define methods on the Agent
@@ -34,14 +34,14 @@ Instances of an Agent are addressed by a unique identifier: that identifier (ID)
 
 ### Agent
 
-Writing an Agent requires you to define a class that extends the `Agent` class from the `agents-sdk` package. An Agent encapsulates all of the logic for an Agent, including how clients can connect to it, how it stores state, the methods it exposes, and any error handling.
+Writing an Agent requires you to define a class that extends the `Agent` class from the Agents SDK package. An Agent encapsulates all of the logic for an Agent, including how clients can connect to it, how it stores state, the methods it exposes, and any error handling.
 
 You can also define your own methods on an Agent: it's technically valid to publish an Agent only has your own methods exposed, and create/get Agents directly from a Worker.
 
 Your own methods can access the Agent's environment variables and bindings on `this.env`, state on `this.setState`, and call other methods on the Agent via `this.yourMethodName`.
 
 ```ts
-import { Agent } from "agents-sdk";
+import { Agent } from "agents";
 
 interface Env {
 	// Define environment variables & bindings here
@@ -361,7 +361,7 @@ function agentFetch(
 
 ### React API
 
-The `agents-sdk` provides a React API for simplifying connection and routing to Agents from front-end frameworks, including React Router (Remix), Next.js, and Astro.
+The Agents SDK provides a React API for simplifying connection and routing to Agents from front-end frameworks, including React Router (Remix), Next.js, and Astro.
 
 #### useAgent
 
@@ -397,7 +397,7 @@ function useAgent<State = unknown>(
 
 ### Chat Agent
 
-The `agents-sdk` exposes an `AIChatAgent` class that extends the `Agent` class and exposes an `onChatMessage` method that simplifies building interactive chat agents.
+The Agents SDK exposes an `AIChatAgent` class that extends the `Agent` class and exposes an `onChatMessage` method that simplifies building interactive chat agents.
 
 You can combine this with the `useAgentChat` React hook from the `agents-sdk/ai-react` package to manage chat state and messages between a user and your Agent(s).
 
@@ -473,6 +473,6 @@ To learn more about how to manage state within an Agent, refer to the documentat
 
 ### Next steps
 
-* [Build a chat Agent](/agents/getting-started/build-a-chat-agent/) using the `agents-sdk` and deploy it to Workers.
+* [Build a chat Agent](/agents/getting-started/build-a-chat-agent/) using the Agents SDK and deploy it to Workers.
 * Learn more [using WebSockets](/agents/api-reference/websockets/) to build interactive Agents and stream data back from your Agent.
-* [Orchestrate asynchronous workflows](/agents/api-reference/run-workflows) from your Agent by combining the `agents-sdk` and [Workflows](/workflows).
+* [Orchestrate asynchronous workflows](/agents/api-reference/run-workflows) from your Agent by combining the Agents SDK and [Workflows](/workflows).
diff --git a/src/content/docs/agents/api-reference/calling-agents.mdx b/src/content/docs/agents/api-reference/calling-agents.mdx
@@ -195,6 +195,6 @@ This ensures we only create Agents for authenticated users, and allows you to va
 ### Next steps
 
 * Review the [API documentation](/agents/api-reference/agents-api/) for the Agents class to learn how to define
-* [Build a chat Agent](/agents/getting-started/build-a-chat-agent/) using the `agents-sdk` and deploy it to Workers.
+* [Build a chat Agent](/agents/getting-started/build-a-chat-agent/) using the Agents SDK and deploy it to Workers.
 * Learn more [using WebSockets](/agents/api-reference/websockets/) to build interactive Agents and stream data back from your Agent.
-* [Orchestrate asynchronous workflows](/agents/api-reference/run-workflows) from your Agent by combining the `agents-sdk` and [Workflows](/workflows).
+* [Orchestrate asynchronous workflows](/agents/api-reference/run-workflows) from your Agent by combining the Agents SDK and [Workflows](/workflows).
diff --git a/src/content/docs/agents/api-reference/client-api.mdx b/src/content/docs/agents/api-reference/client-api.mdx
@@ -76,6 +76,6 @@ TODO
 ### Next steps
 
 * Review the [API documentation](/agents/api-reference/agents-api/) for the Agents class to learn how to define
-* [Build a chat Agent](/agents/getting-started/build-a-chat-agent/) using the `agents-sdk` and deploy it to Workers.
+* [Build a chat Agent](/agents/getting-started/build-a-chat-agent/) using the Agents SDK and deploy it to Workers.
 * Learn more [using WebSockets](/agents/api-reference/websockets/) to build interactive Agents and stream data back from your Agent.
-* [Orchestrate asynchronous workflows](/agents/api-reference/run-workflows) from your Agent by combining the `agents-sdk` and [Workflows](/workflows).
+* [Orchestrate asynchronous workflows](/agents/api-reference/run-workflows) from your Agent by combining the Agents SDK and [Workflows](/workflows).
diff --git a/src/content/docs/agents/api-reference/http-sse.mdx b/src/content/docs/agents/api-reference/http-sse.mdx
@@ -104,11 +104,11 @@ Both WebSockets and Server-Sent Events (SSE) enable real-time communication betw
 * While SSE works well for simple streaming scenarios, WebSockets are better suited for applications requiring minutes or hours of connection time, as they maintain a more stable connection with built-in ping/pong mechanisms to keep connections alive.
 * WebSockets use their own protocol (ws:// or wss://), separating them from HTTP after the initial handshake. This separation allows WebSockets to better handle binary data transmission and implement custom subprotocols for specialized use cases.
 
-If you're unsure of which is better for your use-case, we recommend WebSockets. The [WebSockets API documentation](/agents/api-reference/websockets/) provides detailed information on how to use WebSockets with the `agents-sdk`.
+If you're unsure of which is better for your use-case, we recommend WebSockets. The [WebSockets API documentation](/agents/api-reference/websockets/) provides detailed information on how to use WebSockets with the Agents SDK.
 
 ### Next steps
 
 * Review the [API documentation](/agents/api-reference/agents-api/) for the Agents class to learn how to define
-* [Build a chat Agent](/agents/getting-started/build-a-chat-agent/) using the `agents-sdk` and deploy it to Workers.
+* [Build a chat Agent](/agents/getting-started/build-a-chat-agent/) using the Agents SDK and deploy it to Workers.
 * Learn more [using WebSockets](/agents/api-reference/websockets/) to build interactive Agents and stream data back from your Agent.
-* [Orchestrate asynchronous workflows](/agents/api-reference/run-workflows) from your Agent by combining the `agents-sdk` and [Workflows](/workflows).
+* [Orchestrate asynchronous workflows](/agents/api-reference/run-workflows) from your Agent by combining the Agents SDK and [Workflows](/workflows).
diff --git a/src/content/docs/agents/api-reference/rag.mdx b/src/content/docs/agents/api-reference/rag.mdx
@@ -27,7 +27,7 @@ Here's an example of how to give an Agent retrieval capabilties:
 <TypeScriptExample>
 
 ```ts
-import { Agent } from "agents-sdk";
+import { Agent } from "agents";
 
 interface Env {
 	AI: Ai;
diff --git a/src/content/docs/agents/api-reference/schedule-tasks.mdx b/src/content/docs/agents/api-reference/schedule-tasks.mdx
@@ -18,7 +18,7 @@ You can call `this.schedule` within any method on an Agent, and schedule tens-of
 <TypeScriptExample>
 
 ```ts
-import { Agent } from "agents-sdk"
+import { Agent } from "agents"
 
 export class SchedulingAgent extends Agent {
 	async onRequest(request) {
diff --git a/src/content/docs/agents/api-reference/store-and-sync-state.mdx b/src/content/docs/agents/api-reference/store-and-sync-state.mdx
@@ -26,7 +26,7 @@ Every Agent has built-in state management capabilities. You can set and update t
 <TypeScriptExample>
 
 ```ts
-import { Agent } from "agents-sdk";
+import { Agent } from "agents";
 
 export class MyAgent extends Agent {
   // Update state in response to events
@@ -61,7 +61,7 @@ If you're using TypeScript, you can also provide a type for your Agent's state b
 <TypeScriptExample>
 
 ```ts
-import { Agent } from "agents-sdk";
+import { Agent } from "agents";
 
 interface Env {}
 
@@ -285,6 +285,6 @@ This works because each instance of an Agent has its _own_ database, the state s
 ### Next steps
 
 * Review the [API documentation](/agents/api-reference/agents-api/) for the Agents class to learn how to define
-* [Build a chat Agent](/agents/getting-started/build-a-chat-agent/) using the `agents-sdk` and deploy it to Workers.
+* [Build a chat Agent](/agents/getting-started/build-a-chat-agent/) using the Agents SDK and deploy it to Workers.
 * Learn more [using WebSockets](/agents/api-reference/websockets/) to build interactive Agents and stream data back from your Agent.
-* [Orchestrate asynchronous workflows](/agents/api-reference/run-workflows) from your Agent by combining the `agents-sdk` and [Workflows](/workflows).
+* [Orchestrate asynchronous workflows](/agents/api-reference/run-workflows) from your Agent by combining the Agents SDK and [Workflows](/workflows).
diff --git a/src/content/docs/agents/api-reference/using-ai-models.mdx b/src/content/docs/agents/api-reference/using-ai-models.mdx
@@ -37,7 +37,7 @@ Instead of buffering the entire response, or risking the client disconecting, yo
 <TypeScriptExample filename="src/index.ts">
 
 ```ts
-import { Agent } from "agents-sdk"
+import { Agent } from "agents"
 import { OpenAI } from "openai"
 
 export class MyAgent extends Agent<Env> {
@@ -95,7 +95,7 @@ Workers AI supports streaming responses out-of-the-box by setting `stream: true`
 <TypeScriptExample filename="src/index.ts">
 
 ```ts
-import { Agent } from "agents-sdk"
+import { Agent } from "agents"
 
 interface Env {
 	AI: Ai;
@@ -145,7 +145,7 @@ Model routing allows you to route requests to different AI models based on wheth
 <TypeScriptExample filename="src/index.ts">
 
 ```ts
-import { Agent } from "agents-sdk"
+import { Agent } from "agents"
 
 interface Env {
 	AI: Ai;
@@ -199,7 +199,7 @@ npm install ai @ai-sdk/openai
 <TypeScriptExample filename="src/index.ts">
 
 ```ts
-import { Agent } from "agents-sdk"
+import { Agent } from "agents"
 import { generateText } from 'ai';
 import { openai } from '@ai-sdk/openai';
 
@@ -226,7 +226,7 @@ Agents can stream responses back over HTTP using Server Sent Events (SSE) from w
 <TypeScriptExample filename="src/index.ts">
 
 ```ts
-import { Agent } from "agents-sdk"
+import { Agent } from "agents"
 import { OpenAI } from "openai"
 
 export class MyAgent extends Agent<Env> {
diff --git a/src/content/docs/agents/api-reference/websockets.mdx b/src/content/docs/agents/api-reference/websockets.mdx
@@ -20,7 +20,7 @@ Here's an example of an Agent that echoes back any message it receives:
 <TypeScriptExample>
 
 ```ts
-import { Agent, Connection } from "agents-sdk";
+import { Agent, Connection } from "agents";
 
 export class ChatAgent extends Agent {
 	async onConnect(connection: Connection, ctx: ConnectionContext) {
@@ -114,7 +114,7 @@ Define `onError` and `onClose` methods on your Agent to explicitly handle WebSoc
 <TypeScriptExample>
 
 ```ts
-import { Agent, Connection } from "agents-sdk";
+import { Agent, Connection } from "agents";
 
 export class ChatAgent extends Agent {
  	// onConnect and onMessage methods
diff --git a/src/content/docs/agents/guides/human-in-the-loop.mdx b/src/content/docs/agents/guides/human-in-the-loop.mdx
@@ -5,5 +5,5 @@ external_link: https://github.com/cloudflare/agents/tree/main/guides/anthropic-p
 sidebar:
   order: 3
 head: []
-description: Implement common agent patterns using the `agents-sdk` framework.
+description: Implement common agent patterns using the Agents SDK framework.
 ---
diff --git a/src/content/docs/agents/index.mdx b/src/content/docs/agents/index.mdx
@@ -27,7 +27,7 @@ Build and deploy AI-powered Agents on Cloudflare that can autonomously perform t
 
 #### Ship your first Agent
 
-Use the agent started template to create your first Agent with the `agents-sdk`:
+Use the agent started template to create your first Agent with the Agents SDK:
 
 ```sh
 # install it
@@ -38,23 +38,23 @@ npx wrangler@latest deploy
 
 Head to the guide on [building a chat agent](/agents/getting-started/build-a-chat-agent) to learn how to build and deploy an Agent to prod.
 
-If you're already building on [Workers](/workers/), you can install the `agents-sdk` package directly into an existing project:
+If you're already building on [Workers](/workers/), you can install the `agents` package directly into an existing project:
 
 ```sh
-npm i agents-sdk
+npm i agents
 ```
 
-Dive into the [Agent SDK reference](/agents/api-reference/agents-api/) to learn more about how to use the `agents-sdk` package and defining an `Agent`.
+Dive into the [Agent SDK reference](/agents/api-reference/agents-api/) to learn more about how to use the Agents SDK package and defining an `Agent`.
 
 #### Why build agents on Cloudflare?
 
-We built the `agents-sdk` with a few things in mind:
+We built the Agents SDK with a few things in mind:
 
 - **Batteries (state) included**: Agents come with [built-in state management](/agents/api-reference/store-and-sync-state/), with the ability to automatically sync state between an Agent and clients, trigger events on state changes, and read+write to each Agent's SQL database.
-- **Communicative**: You can connect to an Agent via [WebSockets](/agents/api-reference/websockets/) and stream updates back to client in real-time. Handle a long-running response from a reasoning model, the results of an [asynchronous workflow](/agents/api-reference/run-workflows/), or build a chat app that builds on the `useAgent` hook included in the `agents-sdk`.
+- **Communicative**: You can connect to an Agent via [WebSockets](/agents/api-reference/websockets/) and stream updates back to client in real-time. Handle a long-running response from a reasoning model, the results of an [asynchronous workflow](/agents/api-reference/run-workflows/), or build a chat app that builds on the `useAgent` hook included in the Agents SDK.
 - **Extensible**: Agents are code. Use the [AI models](/agents/api-reference/using-ai-models/) you want, bring-your-own headless browser service, pull data from your database hosted in another cloud, add your own methods to your Agent and call them.
 
-Agents built with `agents-sdk` can be deployed directly to Cloudflare and run on top of [Durable Objects](/durable-objects/) — which you can think of as stateful micro-servers that can scale to tens of millions — and are able to run wherever they need to. Run your Agents close to a user for low-latency interactivity, close to your data for throughput, and/or anywhere in between.
+Agents built with Agents SDK can be deployed directly to Cloudflare and run on top of [Durable Objects](/durable-objects/) — which you can think of as stateful micro-servers that can scale to tens of millions — and are able to run wherever they need to. Run your Agents close to a user for low-latency interactivity, close to your data for throughput, and/or anywhere in between.
 
 ***
 
