twilio-agent-connect 1.0.0 → 1.0.2

package/README.md

@@ -14,53 +14,41 @@
   <div align="center">
     <a href="https://github.com/twilio/twilio-agent-connect-typescript"><img alt="Node.js" src="https://img.shields.io/badge/Node.js-22.13+-339933.svg"/></a>
     <a href="LICENSE"><img alt="License" src="https://img.shields.io/badge/license-MIT-green.svg"/></a>
-    <a href="https://www.twilio.com/docs/platform/tac/quickstart"><img alt="Getting Started" src="https://img.shields.io/badge/Getting%20Started-Quickstart-F22F46.svg"/></a>
+    <a href="https://www.twilio.com/docs/conversations/agent-connect/quickstart"><img alt="Getting Started" src="https://img.shields.io/badge/Getting%20Started-Quickstart-F22F46.svg"/></a>
   </div>
   
   <p>
-    <a href="https://www.twilio.com/docs/platform/tac/overview">Documentation</a>
+    <a href="https://www.twilio.com/docs/conversations/agent-connect">Documentation</a>
     ◆ <a href="https://github.com/twilio/twilio-agent-connect-python">Python SDK</a>
     ◆ <a href="https://github.com/twilio/twilio-agent-connect-typescript">TypeScript SDK</a>
     ◆ <a href="getting_started/examples">Examples</a>
   </p>
 </div>
 
-Seamlessly integrate with Twilio's Memory Store and Conversation Orchestrator to build LLM-powered agents with persistent memory and conversation context.
+Seamlessly integrate with Twilio Conversation Memory and Conversation Orchestrator to build LLM-powered agents with persistent memory and conversation context.
+
+> [!TIP]
+> **Building AI agents on AWS or Microsoft?** Connect them to Twilio's voice, messaging, and conversation context with these dedicated packages:
+> - **[TAC for AWS](https://github.com/twilio/twilio-agent-connect-aws)** — Strands, Bedrock Agents, Bedrock AgentCore
+> - **[TAC for Microsoft](https://github.com/twilio/twilio-agent-connect-microsoft)** — Microsoft Agent Framework, Azure AI Foundry (incl. Voice Live), Azure OpenAI
 
 ---
 
 ## Key Features
 
-- **Messaging Channel Support**: Built-in webhook handling for SMS, RCS, WhatsApp, and Chat conversations
-- **Voice Channel Support**: WebSocket protocol handling for Twilio Voice with ConversationRelay
-- **Outbound Conversations**: Agent-initiated conversations via SMS, RCS, WhatsApp, Chat, and Voice channels
-- **ConversationRelay-Only Mode**: Get started quickly with TAC's voice plumbing (TwiML, WebSocket, callbacks) before adding Conversation Orchestrator
-- **Memory Management**: Automatic integration with Twilio Memory for persistent user context
+- **Multi-Channel Support**: Built-in handling for Voice (ConversationRelay), SMS, RCS, WhatsApp, and Chat
+- **Outbound Conversations**: Agent-initiated conversations across all supported channels
+- **ConversationRelay-Only Mode**: Get started quickly with TAC's voice plumbing (TwiML, WebSocket, callbacks) before adding Conversation Orchestrator or Conversation Memory
+- **Memory Management**: Automatic integration with Twilio Conversation Memory for persistent user context
 - **Conversation Lifecycle**: Automatic tracking of conversation sessions and state
-- **Type-Safe**: Full TypeScript support with strict type checking
-- **Callback-Based**: Simple `onMessageReady` callback for LLM integration with optional memory retrieval
-- **Production Ready**: Comprehensive test coverage and error handling
+- **Human Handoff**: Built-in tool to route conversations to human agents via Twilio Studio Flows (including Flex)
 
 ## Get Started
 
-To get started, set up your Node.js environment (Node.js 22.13.0 or newer required), and then install TAC SDK package.
-
-> [!IMPORTANT]
-> TAC packages are not yet published to npm. We recommend building your agent directly in this repository.
-
-### Build in This Repository
-
-Clone this repository and work within it:
+To get started, set up your Node.js environment (Node.js 22.13.0 or newer required), and then install the [TAC SDK package](https://www.npmjs.com/package/twilio-agent-connect):
 
 ```bash
-git clone https://github.com/twilio/twilio-agent-connect-typescript.git
-cd twilio-agent-connect-typescript
-
-# Install dependencies
-npm install
-
-# Build packages
-npm run build
+npm install twilio-agent-connect
 ```
 
 ## Quick Examples
@@ -77,7 +65,7 @@ make setup  # Open http://localhost:8080
 
 **Option 2: Manual Setup**
 
-You can also create a Memory Store and Conversation Configuration manually through the [Twilio Console](https://1console.twilio.com). For a full walkthrough — credentials, Console navigation, and webhook configuration — see the [TAC Quickstart](https://www.twilio.com/docs/platform/tac/quickstart).
+You can also create a Memory Store and Conversation Configuration manually through the [Twilio Console](https://1console.twilio.com). For a full walkthrough — credentials, Console navigation, and webhook configuration — see the [TAC Quickstart](https://www.twilio.com/docs/conversations/agent-connect/quickstart).
 
 ---
 
@@ -87,15 +75,15 @@ After completing setup, here's a minimal example to get started:
 
 Use the OpenAI SDK to build an AI agent that works across Voice and SMS channels with conversation memory and user context.
 
-First, install the required dependencies in the repository:
+First, install the required dependencies:
 
 ```bash
-npm install openai dotenv
+npm install twilio-agent-connect openai dotenv
 ```
 
 > **Note**: `dotenv` is optional — TAC works with environment variables from any source (`.env` files, Docker, Kubernetes, CI/CD, shell exports, etc.).
 
-Then create your application (e.g., in `getting_started/examples/` or your own directory):
+Then create your application:
 
 ```typescript
 import { config } from 'dotenv';
@@ -140,9 +128,8 @@ tac.onMessageReady(async ({ conversationId, message, memory, session }) => {
     conversationHistory[convId] = [];
   }
 
-  // Build system prompt with memory context
-  const memoryContext = MemoryPromptBuilder.build(memory, session);
-  const systemPrompt = SYSTEM_INSTRUCTIONS + (memoryContext ? `\n\n${memoryContext}` : '');
+  // Build system prompt with memory context using compose()
+  const systemPrompt = MemoryPromptBuilder.compose(SYSTEM_INSTRUCTIONS, memory, session);
 
   conversationHistory[convId].push({ role: 'user', content: message });
 
@@ -199,6 +186,10 @@ For detailed architecture and advanced usage, see [CLAUDE.md](CLAUDE.md).
 - **[Outbound Conversations](getting_started/examples/outbound/)** - Agent-initiated conversations example
 - More examples coming soon
 
+**AWS and Microsoft connectors:**
+- **[TAC for AWS](https://github.com/twilio/twilio-agent-connect-aws)** — `StrandsConnector`, `BedrockConnector`, `BedrockAgentCoreConnector` for AWS Strands, Bedrock Agents, and Bedrock AgentCore
+- **[TAC for Microsoft](https://github.com/twilio/twilio-agent-connect-microsoft)** — `AgentFrameworkConnector` and `VoiceLiveConnector` for Microsoft Agent Framework, Azure AI Foundry (including Voice Live), and Azure OpenAI
+
 **Documentation:**
 - **[CLAUDE.md](CLAUDE.md)** - Architecture, development guide, and API reference
 - **[Getting Started Guide](getting_started/README.md)** - Setup instructions, environment variables, and troubleshooting