Integrations
RAXE integrates with your entire AI stack, from agent frameworks to LLM providers to enterprise SIEM platforms.All integrations use the same underlying detection engine with 514+ rules and ML-based classification. Choose the integration that matches your architecture.
Agent Frameworks
Protect multi-agent systems, RAG pipelines, and autonomous AI applications.LangChain
Most Popular - Protect chains, agents, tools, memory, and RAG pipelines with callback-based scanning.
CrewAI
Multi-agent crew protection with task-level scanning and inter-agent message validation.
AutoGen
Microsoft’s multi-agent framework with conversation-level threat detection.
LlamaIndex
RAG-focused protection for document ingestion, retrieval, and query pipelines.
LiteLLM
100+ LLM Providers - Single integration for OpenAI, Anthropic, Azure, Bedrock, Vertex AI, and more.
DSPy
Stanford’s declarative language model programming framework with signature-level protection.
Portkey
AI gateway integration for unified observability and security across providers.
OpenClaw
Personal AI Assistant - Protect your self-hosted AI across 13+ messaging channels.
LLM Provider Wrappers
Drop-in replacements for native SDKs with built-in threat detection.OpenAI
Drop-in replacement for the OpenAI Python SDK. Same API, added security.
Anthropic
Drop-in replacement for the Anthropic Python SDK with Claude protection.
Enterprise SIEM
Real-time threat data streaming to your security operations center.Splunk
HTTP Event Collector (HEC) integration for real-time threat indexing.
CrowdStrike
Falcon LogScale (Humio) integration for threat correlation.
Microsoft Sentinel
Azure Data Collector API for cloud-native SIEM integration.
ArcSight
SmartConnector CEF format for enterprise SIEM deployments.
CEF (Generic)
Common Event Format over HTTP, UDP, or TCP/TLS syslog.
QRadar
IBM QRadar via CEF format integration.
Web Frameworks
Protect HTTP endpoints and API routes.FastAPI
Middleware and dependency injection patterns.
Flask
Before-request hooks and decorators.
Django
Middleware and Django REST Framework integration.
CI/CD & DevOps
Shift-left security scanning in your deployment pipeline.GitHub Actions
Scan prompts and test data in pull requests.
Pre-commit Hooks
Catch threats before they’re committed.
LLM Providers via LiteLLM
Through our LiteLLM integration, RAXE supports 100+ LLM providers with a single integration:- Cloud Providers
- Open Source
- Specialized
| Provider | Models |
|---|---|
| OpenAI | GPT-4o, GPT-4, GPT-3.5 |
| Anthropic | Claude 3.5, Claude 3, Claude 2 |
| Azure OpenAI | All Azure-hosted models |
| Google Vertex AI | Gemini Pro, PaLM 2 |
| AWS Bedrock | Claude, Llama, Titan |
| Cohere | Command, Embed |
| Mistral AI | Mistral Large, Medium, Small |
Quick Comparison
| Integration | Best For | Scan Points | Install |
|---|---|---|---|
| LangChain | Agent apps, RAG | Prompts, tools, memory | pip install raxe[langchain] |
| LiteLLM | Multi-provider apps | All LLM calls | pip install raxe[litellm] |
| OpenAI Wrapper | Simple OpenAI apps | Chat completions | pip install raxe[wrappers] |
| CrewAI | Multi-agent crews | Agent messages, tasks | pip install raxe[crewai] |
| SIEM | Enterprise SOC | All detections | See SIEM docs |
Need Help Choosing?
I'm building a RAG application
I'm building a RAG application
Use LangChain or LlamaIndex depending on your framework. Both provide deep integration with document retrieval and query pipelines.
I'm using multiple LLM providers
I'm using multiple LLM providers
Use LiteLLM - it provides a unified interface for 100+ providers with RAXE protection built in.
I just want to protect OpenAI calls
I just want to protect OpenAI calls
Use the OpenAI Wrapper - it’s a drop-in replacement with zero code changes beyond the import.
I need enterprise SIEM integration
I need enterprise SIEM integration
See our SIEM documentation for Splunk, CrowdStrike, Sentinel, and CEF integrations.
I'm building multi-agent systems
I'm building multi-agent systems
Use CrewAI or AutoGen depending on your framework. Both support inter-agent message scanning.