AWS Bedrock AgentCore
OfficialFreeRun browser automation on AWS with ease.
Free · Opens the source repo
What AWS Bedrock AgentCore does
AWS Bedrock AgentCore enables users to execute browser automation tasks in a cloud environment hosted by AWS. By leveraging the agent-browser command line tool, you can run all standard browser automation commands seamlessly in the cloud, allowing for scalability and reliability. This is particularly useful for developers and testers who need to run automated scripts without the overhead of managing local browser instances.
The setup process is straightforward, as AWS credentials are resolved automatically through environment variables or the AWS CLI. If you already have a working AWS setup, you can start using AgentCore without additional configuration. The tool supports persistent browser profiles, which means you can maintain session states across multiple runs, making it ideal for tasks that require authentication or state management.
One of the key features of AgentCore is the Live View functionality, which allows you to monitor your browser sessions in real time via the AWS Console. This can be invaluable for debugging and ensuring that your automation scripts are performing as expected. Additionally, you can specify the AWS region for your browser sessions, providing flexibility in terms of where your resources are hosted.
Overall, AWS Bedrock AgentCore is designed for developers and QA engineers who require a robust and scalable solution for browser automation in the cloud. It simplifies the process of running automated tests and scripts by offloading the browser management to AWS, allowing you to focus on writing and maintaining your automation code.
When to use it
Use this skill when you need to run browser automation tasks in a scalable cloud environment, especially when working with AWS.
When not to use it
Avoid this skill if you do not have AWS credentials or if you prefer local browser automation without cloud dependencies.
What you can build with it
Automated Testing in the Cloud
Run your automated browser tests in the cloud to leverage AWS's scalability and reliability.
Session Management for Web Applications
Maintain persistent login sessions for web applications across multiple automation runs using persistent profiles.
Real-Time Monitoring of Automation Tasks
Use the Live View feature to observe your browser automation tasks as they execute in real time.
How to install AWS Bedrock AgentCore
View source1. Install with the skills CLI
npx skills add vercel-labs/agent-browser/agentcore --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by vercel-labsAWS Bedrock AgentCore
Run agent-browser on cloud browser sessions hosted by AWS Bedrock AgentCore. All standard agent-browser commands work identically; the only difference is where the browser runs.
Setup
Credentials are resolved automatically:
- Environment variables (
AWS_ACCESS_KEY_ID,AWS_SECRET_ACCESS_KEY, optionallyAWS_SESSION_TOKEN) - AWS CLI fallback (
aws configure export-credentials), which supports SSO, IAM roles, and named profiles
No additional setup is needed if the user already has working AWS credentials.
Core Workflow
# Open a page on an AgentCore cloud browser
agent-browser -p agentcore open https://example.com
# Everything else is the same as local Chrome
agent-browser snapshot -i
agent-browser click @e1
agent-browser screenshot page.png
agent-browser close
Environment Variables
| Variable | Description | Default |
|---|---|---|
AGENTCORE_REGION | AWS region | us-east-1 |
AGENTCORE_BROWSER_ID | Browser identifier | aws.browser.v1 |
AGENTCORE_PROFILE_ID | Persistent browser profile (cookies, localStorage) | (none) |
AGENTCORE_SESSION_TIMEOUT | Session timeout in seconds | 3600 |
AWS_PROFILE | AWS CLI profile for credential resolution | default |
Persistent Profiles
Use AGENTCORE_PROFILE_ID to persist browser state across sessions. This is useful for maintaining login sessions:
# First run: log in
AGENTCORE_PROFILE_ID=my-app agent-browser -p agentcore open https://app.example.com/login
agent-browser snapshot -i
agent-browser fill @e1 "user@example.com"
agent-browser fill @e2 "password"
agent-browser click @e3
agent-browser close
# Future runs: already authenticated
AGENTCORE_PROFILE_ID=my-app agent-browser -p agentcore open https://app.example.com/dashboard
Live View
When a session starts, AgentCore prints a Live View URL to stderr. Open it in a browser to watch the session in real time from the AWS Console:
Session: abc123-def456
Live View: https://us-east-1.console.aws.amazon.com/bedrock-agentcore/browser/aws.browser.v1/session/abc123-def456#
Region Selection
# Default: us-east-1
agent-browser -p agentcore open https://example.com
# Explicit region
AGENTCORE_REGION=eu-west-1 agent-browser -p agentcore open https://example.com
Credential Patterns
# Explicit credentials (CI/CD, scripts)
export AWS_ACCESS_KEY_ID=AKIA...
export AWS_SECRET_ACCESS_KEY=...
agent-browser -p agentcore open https://example.com
# SSO (interactive)
aws sso login --profile my-profile
AWS_PROFILE=my-profile agent-browser -p agentcore open https://example.com
# IAM role / default credential chain
agent-browser -p agentcore open https://example.com
Using with AGENT_BROWSER_PROVIDER
Set the provider via environment variable to avoid passing -p agentcore on every command:
export AGENT_BROWSER_PROVIDER=agentcore
export AGENTCORE_REGION=us-east-2
agent-browser open https://example.com
agent-browser snapshot -i
agent-browser click @e1
agent-browser close
Common Issues
"Failed to run aws CLI" means AWS CLI is not installed or not in PATH. Either install it or set AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY directly.
"AWS CLI failed: ... Run 'aws sso login'" means SSO credentials have expired. Run aws sso login to refresh them.
Session timeout: The default is 3600 seconds (1 hour). For longer tasks, increase with AGENTCORE_SESSION_TIMEOUT=7200.
Frequently asked questions about AWS Bedrock AgentCore
Similar skills
Spring Boot Testing
Master testing techniques for Spring Boot 4 applications.
GitHub Issues
Manage GitHub issues efficiently with MCP tools.
Geofeed Tuner
Optimize your IP geolocation feeds in CSV format.
Batch Files
Master Windows batch scripting for automation and task management.
Adobe Illustrator Scripting
Automate your Illustrator workflows with ExtendScript.
Plugin Structure
Create and organize Claude Code plugins effectively.