BedrockInvokeAgentTool
The BedrockInvokeAgentTool
enables CrewAI agents to invoke Amazon Bedrock Agents and leverage their capabilities within your workflows.
Installation
Requirements
- AWS credentials configured (either through environment variables or AWS CLI)
boto3
andpython-dotenv
packages- Access to Amazon Bedrock Agents
Usage
Here’s how to use the tool with a CrewAI agent:Tool Arguments
Argument | Type | Required | Default | Description |
---|---|---|---|---|
agent_id | str | Yes | None | The unique identifier of the Bedrock agent |
agent_alias_id | str | Yes | None | The unique identifier of the agent alias |
session_id | str | No | timestamp | The unique identifier of the session |
enable_trace | bool | No | False | Whether to enable trace for debugging |
end_session | bool | No | False | Whether to end the session after invocation |
description | str | No | None | Custom description for the tool |
Environment Variables
Advanced Usage
Multi-Agent Workflow with Session Management
Use Cases
Hybrid Multi-Agent Collaborations
- Create workflows where CrewAI agents collaborate with managed Bedrock agents running as services in AWS
- Enable scenarios where sensitive data processing happens within your AWS environment while other agents operate externally
- Bridge on-premises CrewAI agents with cloud-based Bedrock agents for distributed intelligence workflows
Data Sovereignty and Compliance
- Keep data-sensitive agentic workflows within your AWS environment while allowing external CrewAI agents to orchestrate tasks
- Maintain compliance with data residency requirements by processing sensitive information only within your AWS account
- Enable secure multi-agent collaborations where some agents cannot access your organization’s private data
Seamless AWS Service Integration
- Access any AWS service through Amazon Bedrock Actions without writing complex integration code
- Enable CrewAI agents to interact with AWS services through natural language requests
- Leverage pre-built Bedrock agent capabilities to interact with AWS services like Bedrock Knowledge Bases, Lambda, and more
Scalable Hybrid Agent Architectures
- Offload computationally intensive tasks to managed Bedrock agents while lightweight tasks run in CrewAI
- Scale agent processing by distributing workloads between local CrewAI agents and cloud-based Bedrock agents
Cross-Organizational Agent Collaboration
- Enable secure collaboration between your organization’s CrewAI agents and partner organizations’ Bedrock agents
- Create workflows where external expertise from Bedrock agents can be incorporated without exposing sensitive data
- Build agent ecosystems that span organizational boundaries while maintaining security and data control