Integrations | LangWatch
Integrations
Plug into your stack.
Trace, evaluate, ship.
25+ first-class integrations. Python and TypeScript SDKs, every major model provider, every agent framework worth using, OpenTelemetry-native end to end.
Read the integration docs SDK quickstart
SDKs
Languages
Wrap your agent in one line. Python and TypeScript, both OpenTelemetry-native.
Python SDK
pip install langwatch · decorators for traces, evals, and prompts.
Read the guide
TypeScript SDK
npm i langwatch · works in Node, edge runtimes, and the browser.
Read the guide
OpenTelemetry & REST
Send spans from any language. Already on OTEL? Point the exporter at LangWatch.
OpenTelemetry
Native OTLP ingest. Use any OTEL SDK, GenAI semconv supported.
Read the guide
REST API
Direct HTTP for environments where an SDK is not an option.
Read the guide
LLMs & model gateways
Trace any provider. The AI Gateway gives you one endpoint, virtual keys, fallback, and budgets across all of them.
OpenAI
GPT-5, GPT-4.1, o-series. Auto-instrumented end to end.
Read the guide
Anthropic
Claude Opus, Sonnet, Haiku. Tool use and streaming captured.
Read the guide
Google Gemini
Gemini and Vertex AI traces with prompts, tools, and usage.
Read the guide
AWS Bedrock
Bedrock Runtime captured with model, region, and token usage.
Read the guide
Azure OpenAI
Azure-deployed OpenAI models with deployment metadata.
Read the guide
Vertex AI
Google Cloud Vertex AI for Gemini and partner models.
Read the guide
Groq
Ultra-low-latency inference, traced like any other provider.
Read the guide
Ollama
Local models traced through the OpenAI-compatible adapter.
Read the guide
LiteLLM
Hit 100+ providers behind one OpenAI-compatible interface.
Read the guide
Frameworks & orchestrators
Drop LangWatch into whatever you build agents with. Auto-instrumentation captures every step, tool call, and handoff.
OpenAI Agents
The official Agents SDK, traced step by step.
Read the guide
LangGraph
Graph-state agents with every node, edge, and retry captured.
Read the guide
LangChain
Chains, runnables, and callbacks instrumented automatically.
Read the guide
CrewAI
Multi-agent crews with role, task, and tool-call visibility.
Read the guide
Pydantic AI
Type-safe agents with structured I/O and tool traces.
Read the guide
Agno
High-performance Python framework with native tracing.
Read the guide
Mastra
TypeScript-first agent framework with full OTEL bridge.
Read the guide
Vercel AI SDK
streamText, generateText, and tool calls traced end to end.
Read the guide
Google ADK
The Agent Development Kit, instrumented for production.
Read the guide
LangFlow
Visual flows pushed through LangWatch with one toggle.
Read the guide
Flowise
No-code agent builder with the LangWatch analytics tile.
Read the guide
Prompt optimization
Run real optimizers against your traces and datasets — not vibes.
DSPy
Optimize prompts toward your own metrics with the Optimization Studio.
Read the guide
Same three lines. Whatever your stack.
Install the SDK, set one environment variable, wrap your agent. Every framework on this page lands the same way: traces, evals, and prompt history in the platform without touching your call sites.
Python TypeScript
import langwatch
@langwatch.trace()
def run_agent(query: str) -> str:
# your agent, untouched
...
Don't see your stack? It probably works anyway.
If it speaks OpenTelemetry, it speaks LangWatch. Point your exporter at our OTLP endpoint, or open a ticket and we'll wire it up with you.