Get Started

Request an API key

Integrate with your agent

Build your next agent with evals, observability, and replays.

Introduction

AgentOps

AgentOps is the developer favorite platform for testing, debugging, and deploying AI agents and LLM apps.

Get started with AgentOps in minutes with just 2 lines of code for basic monitoring, and explore powerful decorators for custom tracing.

Quickstart

Examples of AgentOps with various integrations

Examples

Chat with the AgentOps documentation directly from your IDE using the Mintlify MCP Docs Server.

MCP Docs

MCP server for accessing AgentOps trace and span data

MCP Server

Understanding the fundamental concepts of AgentOps

Core Concepts

Use decorators to track activities in your agent system

Decorators

Effectively manage traces in your agent workflow

Traces

Understanding the different types of spans in AgentOps

Spans

Organize and filter your sessions with customizable tags

Agno

Track and analyze your Anthropic API calls with AgentOps

Anthropic

Integrate AgentOps with Microsoft AutoGen for multi-agent workflow tracking

AutoGen

AgentOps and CrewAI teamed up to make monitoring Crew agents dead simple.

CrewAI

Track and analyze your Google Agent Development Kit (ADK) AI agents with AgentOps

Google ADK

Monitor and analyze your Google Gemini API calls with AgentOps

Google Generative AI

Track your LangChain agents with AgentOps

LangChain

Track and analyze your LangGraph workflows with AgentOps

LangGraph

AgentOps works seamlessly with LlamaIndex, a framework for building context-augmented generative AI applications with LLMs.

LlamaIndex

Track and analyze your LiteLLM calls across multiple providers with AgentOps

LiteLLM

Track and monitor Mem0 memory operations with AgentOps

Mem0

Track and analyze your OpenAI API calls with AgentOps

OpenAI

AgentOps and OpenAI Agents SDK integration for powerful multi-agent workflow monitoring.

OpenAI Agents SDK

AgentOps integration with the OpenAI Agents SDK for TypeScript/JavaScript.

OpenAI Agents JS

Track and analyze your Smolagents AI agents with AgentOps

Smolagents

Track and analyze your IBM Watsonx.ai API calls with AgentOps

IBM Watsonx.ai

Track and analyze your xAI Grok API calls with AgentOps

xAI (Grok)

Dashboard

All functions and classes exposed in the top layer of the SDK

SDK Reference

Get started with the AgentOps TypeScript SDK for Node.js applications

TypeScript SDK

Advanced Configuration

Use AgentOps traces as Python context managers for automatic lifecycle management

Context Managers

Tracking LLM Calls using the AgentOps SDK

Tracking LLM Calls

Associate operations with specific named agents

Tracking Agents

Track operations and LLM calls in your agent applications.

Recording Operations

Create custom traces with the @trace decorator

Trace Decorator

Advanced trace management with start_trace and end_trace methods

Manual Trace Control

Read-only HTTP API for accessing AgentOps trace and span data

Public API

Automatically collected information about the environment where your agent runs

Host Environment

Start using AgentOps with just 2 lines of code

An in-depth exploration of the foundational elements and operational dynamics of AgentOps, highlighting its architecture and constituent components.

Seemingly magic tools that can be added to functions and classes for easier instrumenting.

Detailed breakdown of initializing AgentOps and managing sessions.

Sessions

AgentOps uses spans to track different types of operations in your agent workflows.

Tags are a fantastic way to organize your Sessions based on data known by the developer but not by AgentOps. Ex: `paid-user`, `v3`, `recruiter-agent`

Agents sdk

Observe AI21's latest Jamba family of models with AgentOps 

AI21

AgentOps provides first class support for Anthropic's latest models

Track and analyze CAMEL agents with AgentOps

Camel AI

AgentOps provides first class support for Cohere

Cohere

Explore Google DeepMind's Gemini with observation via AgentOps

Gemini

AgentOps provides first class support for Groq

Groq

Monitor your Haystack agents with AgentOps

Haystack

AgentOps provides first class support for LangChain applications

Llama Stack is a framework from Meta AI for building Agentic applications.

Llama Stack

Call the latest models using the OpenAI format including:   Llama, Mistral, Claude, Gemini, Gemma, DALL-E, Whisper

AgentOps provides first class support for Mistral AI's models

Mistral

AgentOps and MultiOn have collaborated to simplify the monitoring of autonomous browser agents.

MultiOn

AgentOps provides first class support for Ollama

Ollama

AgentOps provides first class support for OpenAI's GPT family of models

REST API

Track HuggingFace's smolagents with AgentOps seamlessly

smolagents

Build powerful web search agents with SwarmZero and AgentOps monitoring

SwarmZero

First class support for Microsoft TaskWeaver

TaskWeaver

Observe the power of Grok and Grok Vision with AgentOps

Use the `@agent` decorator to create agent spans

Instrument your code with decorators to track operations, tasks, and workflows.

Getting Started

Concepts

Integrations

Usage

Other Info

Introduction

Get Started

Quick Start

Request an API key

Integrate with your agent

Quick Start

Recording Events

Getting Started

Concepts

Integrations

Usage

Other Info

​Get Started

Quick Start

​Request an API key

​Integrate with your agent

Quick Start

Recording Events

Get Started

Request an API key

Integrate with your agent