Installation & Usage

Install this tool and use it with the AI SDK

1. Install the package

npm install bedrock-agentcore

pnpm add bedrock-agentcore

yarn add bedrock-agentcore

bun add bedrock-agentcore

deno add npm:bedrock-agentcore

2. Import the tool

import { BrowserTools } from 'bedrock-agentcore';

3. Use with AI SDK

import { generateText } from 'ai';
import { openai } from '@ai-sdk/openai';
import { BrowserTools } from 'bedrock-agentcore';

const result = await generateText({
  model: openai('gpt-4o'),
  tools: { BrowserTools },
  prompt: 'Your prompt here...',
});

console.log(result.text);

AI Agent Integration

How AI agents can use this tool

Use Case

Use for browser automation and web interaction tasks

Examples

Fill web forms
Navigate websites
Extract dynamic content

Parameters

Available configuration options

No schema

No schema available for this tool.

README

Bedrock AgentCore SDK for TypeScript

Deploy AI agents to AWS with VM-level isolation and zero infrastructure

Documentation | Samples | Python SDK

Why AgentCore?

Zero infrastructure — No servers to provision, no containers to manage, no scaling to configure.
Session isolation — Each agent session runs in its own VM. No shared state, no noisy neighbors.
Long-lived sessions — Sessions persist across requests. Your agent maintains context without external storage.
Managed tools — Secure code execution and browser automation, ready to use.
Credential management — Centralized API keys and OAuth tokens, injected at runtime.

Works with Strands Agents, Vercel AI SDK, or any framework.

Quick Start

npm install bedrock-agentcore @strands-agents/sdk

import { BedrockAgentCoreApp } from 'bedrock-agentcore/runtime'
import { Agent, BedrockModel } from '@strands-agents/sdk'
import { z } from 'zod'

const agent = new Agent({
  model: new BedrockModel({ modelId: 'global.amazon.nova-2-lite-v1:0' }),
})

const app = new BedrockAgentCoreApp({
  invocationHandler: {
    requestSchema: z.object({ prompt: z.string() }),
    process: async function* (request) {
      for await (const event of agent.stream(request.prompt)) {
        if (event.delta?.text) yield { text: event.delta.text }
      }
    },
  },
})

app.run()

BedrockAgentCoreApp creates an AgentCore Runtime-compliant server—handling request parsing, streaming responses, and session management for seamless deployment.

Tools

Give your agent secure code execution with three lines:

import { CodeInterpreterTools } from 'bedrock-agentcore/tools/code-interpreter/strands'
import { Agent, BedrockModel } from '@strands-agents/sdk'

const codeInterpreter = new CodeInterpreterTools({ region: 'us-east-1' })

const agent = new Agent({
  model: new BedrockModel({ modelId: 'global.amazon.nova-2-lite-v1:0' }),
  tools: codeInterpreter.getTools(),
})

// Agent can now execute code in a secure sandboxed environment

Features

Runtime — Secure, session-isolated compute → Examples
Code Interpreter — Execute Python/JS/TS in a sandbox → Examples
Browser — Cloud-based web automation → Examples
Identity — Manage API keys and OAuth tokens → Examples
Memory — Persistent knowledge across sessions (coming soon)
Gateway — Transform APIs into MCP tools (coming soon)
Observability — OpenTelemetry tracing (coming soon)

Installation

npm install bedrock-agentcore

Prerequisites: Node.js 20+, AWS credentials, AgentCore access

Deployment

Sample Applications — Working examples with deployment templates
CloudFormation — Infrastructure as code
AWS CDK — Infrastructure as code
Deployment Guide — Step-by-step walkthrough

Resources

License

Apache 2.0 — see LICENSE

Contributing · Security

BrowserTools

This tool is currently broken

Interactive Playground