AI Observability integrations
- Latest Dynatrace
- Reference
- 2-min read
Dynatrace integrates with a broad range of AI and ML technologies: agent frameworks, model providers, coding agents, vector stores, orchestration libraries, compute platforms, and AI gateways.
Don't see your technology listed below? Browse the full, continuously updated catalog in Dynatrace Hub.
AI agents
Amazon Bedrock AgentCore
Monitor and trace your Amazon Bedrock AgentCore Agents.
Amazon Bedrock AgentCore Gateway
Monitor and trace agent traffic through the Amazon Bedrock AgentCore Gateway.
AWS Strands Agents
Monitor and trace your AWS Strands Agents.
Claude Platform
Send Claude API and Claude SDK traces to Dynatrace.
Google ADK
Monitor your Google Agent Development Kit.
LangGraph
Monitor and trace your LangChain Agents.
MCP AI Agent monitoring
Monitoring and tracing of agents communicating via MCP.
Microsoft Agent Framework
Send agent traces and metrics to Dynatrace.
OGX (Llama Stack)
Trace OGX agents and model calls with OneAgent or OpenTelemetry.
OpenAI Agents
Monitor and trace your OpenAI Agents.
Pydantic AI
Monitor and trace your Pydantic AI Agents.
Model providers and platforms
Amazon Bedrock
Observe end-to-end generative AI models provided by Amazon Bedrock.
Amazon Nova
Monitor and trace Amazon Nova models running on Amazon Bedrock.
Amazon SageMaker
Build, train, and deploy machine learning (ML) models quickly.
Amazon Textract
Makes it easy to add document text detection and analysis to your applications.
Amazon Translate
Text translation service using machine learning to provide high-quality translation on demand.
Anthropic
Monitor end-to-end your Anthropic services such as Haiku, Sonnet, and Opus.
Azure AI Foundry
End-to-end observability for GenAI & LLM applications built with Azure.
Cohere
Observe end-to-end generative and retrieval models provided by Cohere.
CrewAI
Monitor CrewAI workloads and AI Agents.
DeepSeek
End-to-end observability for DeepSeek models on Amazon Bedrock like R1, V3.
Gemini
Observe end-to-end multimodal AI models provided by Google Gemini.
Groq
Monitor your services built with Groq AI inference models.
Hugging Face
Observe and monitor AI models, datasets, and apps built with Hugging Face.
IBM watsonx AI
End-to-end monitoring for applications built with the IBM watsonx AI platform.
Mistral AI
Monitor your applications built with Mistral AI's frontier models.
Nutanix AI
Monitor Nutanix AI agentic and LLM workloads across infrastructure and models.
NVIDIA NIM
Monitor accelerated inference microservices to run AI models on NVIDIA GPU.
Ollama
Monitor Ollama AI models end-to-end, including Llama, Mistral, Orca, and more.
OpenAI
Monitor your OpenAI & Azure OpenAI services such as GPT, o1, DALL-E, ChatGPT.
Red Hat OpenShift AI
Monitor and observe end-to-end your app powered by Red Hat OpenShift AI platform.
Replicate
Monitor and measure the API performance of your apps built with Replicate.
Together AI
End-to-end observability of your GenAI stack built with Together AI.
Vertex AI Studio
Monitor your generative AI applications built with Google Vertex AI Studio.
AI coding agent monitoring
Antigravity CLI Monitoring
Monitor Antigravity CLI activity and developer workflows.
Claude Code Agent monitoring
Observe Claude Code sessions, tool use, and coding-agent activity.
Cursor monitoring
Monitor Cursor usage, tokens, cost, and errors with a ready-made dashboard.
GitHub Copilot SDK Monitoring
Monitor GitHub Copilot usage via the SDK.
Kiro monitoring
Monitor Kiro credit usage, messages, and user adoption.
OpenAI Codex Monitoring
Observe OpenAI Codex usage and code-generation activity.
OpenClaw Monitoring
Monitor activity from the OpenClaw coding agent.
OpenCode Monitoring
Observe activity from the OpenCode coding agent.
VS Code Copilot Chat monitoring
Monitor VS Code Copilot Chat agents, tokens, and cost with native OpenTelemetry.
Data management and vector stores
Chroma
Monitor the Chroma open-source vector database.
Elasticsearch
Monitor Elasticsearch Clusters, Nodes, Indexes, remotely or locally, via API.
LanceDB
Observe queries against the LanceDB embedded vector store.
Marqo
Gain insights into your embedding models built with Marqo.
Milvus
Observe Milvus, a high-performance vector database for production AI workloads.
Pinecone
Monitor performance and usage of the Pinecone managed vector database.
Qdrant
Observe Qdrant, a high-performance vector search engine.
Weaviate
Monitor Weaviate, an open-source vector database with built-in semantic search.
Orchestration and prompt engineering frameworks
Haystack
Open-source framework for building production-ready LLM applications.
LangChain
Framework for building applications with large language models.
LlamaIndex
Data framework for building RAG and agentic LLM applications.
n8n
Build agentic workflows based on reliable, real-time production insights.
Infrastructure and compute resources
Google Cloud Tensor Processing Units
Monitor Google Cloud TPUs used to accelerate AI workloads.
NVIDIA GPU
Monitor NVIDIA GPU utilization across your AI infrastructure.
TensorFlow Keras
Observe TensorFlow Keras model training and serving.
vLLM
Observe vLLM, a high-throughput inference engine for large language models.
