New to RAXE? Start with the Quickstart and learn how detection works.
Overview
RAXE provides think-time security for CrewAI multi-agent crews — real-time threat detection during agent inference, before task execution. Protect agent-to-agent communications, task handoffs, and tool invocations. What RAXE scans:- Agent messages and reasoning
- Task outputs and handoffs
- Tool inputs and outputs
- Inter-agent communications
Installation
Quick Start
quick_start.py
Using Callbacks
Alternatively, use callbacks directly in your crew:callbacks.py
Configuration
config.py
Available Modes
| Mode | Description |
|---|---|
ScanMode.LOG_ONLY | Log threats, allow execution (default) |
ScanMode.BLOCK_ON_THREAT | Block any detected threat |
ScanMode.BLOCK_ON_HIGH | Block HIGH and CRITICAL severity |
ScanMode.BLOCK_ON_CRITICAL | Block only CRITICAL severity |
Tool Scanning
Automatically scan tool inputs and outputs:tool_scanning.py
Threat Callbacks
Handle detected threats with custom callbacks:threat_callbacks.py
Error Handling
error_handling.py
Advanced Options
advanced.py
Best Practices
Start with log-only mode
Start with log-only mode
Monitor threats before enabling blocking:
log_only.py
Wrap tools for comprehensive coverage
Wrap tools for comprehensive coverage
Enable tool wrapping for full protection:
wrap_tools.py
Use appropriate blocking threshold
Use appropriate blocking threshold
Choose blocking threshold based on risk tolerance:
thresholds.py
Supported Versions
| CrewAI Version | Status |
|---|---|
| crewai >= 0.28.0 | Supported |
