Agentops

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

From AgentOps-AI·Updated May 29, 2026·View on GitHub·

AgentOps helps developers build, evaluate, and monitor AI agents. From prototype to production. The project is written primarily in Python, distributed under the MIT License license, first published in 2023. It has gained significant community traction with 5,584 stars and 586 forks on GitHub. Key topics include: agent, agentops, agents-sdk, ai, anthropic.

Latest release: 0.4.21

August 29, 2025View Changelog →

<div align="center"> <a href="https://agentops.ai?ref=gh"> <img src="docs/images/external/logo/github-banner.png" alt="Logo"> </a> </div> <div align="center"> <em>Observability and DevTool platform for AI Agents</em> </div> <br /> <div align="center"> <a href="https://pepy.tech/project/agentops"> <img src="https://static.pepy.tech/badge/agentops/month" alt="Downloads"> </a> <a href="https://github.com/agentops-ai/agentops/issues"> <img src="https://img.shields.io/github/commit-activity/m/agentops-ai/agentops" alt="git commit activity"> </a> <img src="https://img.shields.io/pypi/v/agentops?&color=3670A0" alt="PyPI - Version"> <a href="https://opensource.org/licenses/MIT"> <img src="https://img.shields.io/badge/License-MIT-yellow.svg?&color=3670A0" alt="License: MIT"> </a> <a href="https://smithery.ai/server/@AgentOps-AI/agentops-mcp"> <img src="https://smithery.ai/badge/@AgentOps-AI/agentops-mcp"/> </a> </div> <p align="center"> <a href="https://twitter.com/agentopsai/"> <img src="https://img.shields.io/twitter/follow/agentopsai?style=social" alt="Twitter" style="height: 20px;"> </a> <a href="https://discord.gg/FagdcwwXRR"> <img src="https://img.shields.io/badge/discord-7289da.svg?style=flat-square&logo=discord" alt="Discord" style="height: 20px;"> </a> <a href="https://app.agentops.ai/?ref=gh"> <img src="https://img.shields.io/badge/Dashboard-blue.svg?style=flat-square" alt="Dashboard" style="height: 20px;"> </a> <a href="https://docs.agentops.ai/introduction"> <img src="https://img.shields.io/badge/Documentation-orange.svg?style=flat-square" alt="Documentation" style="height: 20px;"> </a> <a href="https://entelligence.ai/AgentOps-AI&agentops"> <img src="https://img.shields.io/badge/Chat%20with%20Docs-green.svg?style=flat-square" alt="Chat with Docs" style="height: 20px;"> </a> </p> <div align="center"> <video src="https://github.com/user-attachments/assets/dfb4fa8d-d8c4-4965-9ff6-5b8514c1c22f" width="650" autoplay loop muted></video> </div> <br/>

AgentOps helps developers build, evaluate, and monitor AI agents. From prototype to production.

Open Source

The AgentOps app is open source under the MIT license. Explore the code in our app directory.

Key Integrations 🔌


📊 Replay Analytics and Debugging	Step-by-step agent execution graphs
💸 LLM Cost Management	Track spend with LLM foundation model providers
🤝 Framework Integrations	Native Integrations with CrewAI, AG2 (AutoGen), Agno, LangGraph, & more
⚒️ Self-Host	Want to run AgentOps on your own cloud? You're covered

Quick Start ⌨️

bash
pip install agentops

Session replays in 2 lines of code

Initialize the AgentOps client and automatically get analytics on all your LLM calls.

Get an API key

python
import agentops

# Beginning of your program (i.e. main.py, __init__.py)
agentops.init( < INSERT YOUR API KEY HERE >)

...

# End of program
agentops.end_session('Success')

All your sessions can be viewed on the AgentOps dashboard
<br/>

Self-Hosting

Looking to run the full AgentOps app (Dashboard + API backend) on your machine? Follow the setup guide in app/README.md:

Run the App and Backend (Dashboard + API)

<details> <summary>Agent Debugging</summary> <a href="https://app.agentops.ai?ref=gh"> <img src="docs/images/external/app_screenshots/session-drilldown-metadata.png" style="width: 90%;" alt="Agent Metadata"/> </a> <a href="https://app.agentops.ai?ref=gh"> <img src="docs/images/external/app_screenshots/chat-viewer.png" style="width: 90%;" alt="Chat Viewer"/> </a> <a href="https://app.agentops.ai?ref=gh"> <img src="docs/images/external/app_screenshots/session-drilldown-graphs.png" style="width: 90%;" alt="Event Graphs"/> </a> </details> <details> <summary>Session Replays</summary> <a href="https://app.agentops.ai?ref=gh"> <img src="docs/images/external/app_screenshots/session-replay.png" style="width: 90%;" alt="Session Replays"/> </a> </details> <details> <summary>Summary Analytics</summary> <a href="https://app.agentops.ai?ref=gh"> <img src="docs/images/external/app_screenshots/overview.png" style="width: 90%;" alt="Summary Analytics"/> </a> <a href="https://app.agentops.ai?ref=gh"> <img src="docs/images/external/app_screenshots/overview-charts.png" style="width: 90%;" alt="Summary Analytics Charts"/> </a> </details>

First class Developer Experience

Add powerful observability to your agents, tools, and functions with as little code as possible: one line at a time.
<br/>
Refer to our documentation

python
# Create a session span (root for all other spans)
from agentops.sdk.decorators import session

@session
def my_workflow():
    # Your session code here
    return result

python
# Create an agent span for tracking agent operations
from agentops.sdk.decorators import agent

@agent
class MyAgent:
    def __init__(self, name):
        self.name = name
        
    # Agent methods here

python
# Create operation/task spans for tracking specific operations
from agentops.sdk.decorators import operation, task

@operation  # or @task
def process_data(data):
    # Process the data
    return result

python
# Create workflow spans for tracking multi-operation workflows
from agentops.sdk.decorators import workflow

@workflow
def my_workflow(data):
    # Workflow implementation
    return result

python
# Nest decorators for proper span hierarchy
from agentops.sdk.decorators import session, agent, operation

@agent
class MyAgent:
    @operation
    def nested_operation(self, message):
        return f"Processed: {message}"
        
    @operation
    def main_operation(self):
        result = self.nested_operation("test message")
        return result

@session
def my_session():
    agent = MyAgent()
    return agent.main_operation()

All decorators support:

Input/Output Recording
Exception Handling
Async/await functions
Generator functions
Custom attributes and names

Integrations 🦾

OpenAI Agents SDK 🖇️

Build multi-agent systems with tools, handoffs, and guardrails. AgentOps natively integrates with the OpenAI Agents SDKs for both Python and TypeScript.

Python

bash
pip install openai-agents

TypeScript

bash
npm install agentops @openai/agents

CrewAI 🛶

Build Crew agents with observability in just 2 lines of code. Simply set an AGENTOPS_API_KEY in your environment, and your crews will get automatic monitoring on the AgentOps dashboard.

bash
pip install 'crewai[agentops]'

AG2 🤖

With only two lines of code, add full observability and monitoring to AG2 (formerly AutoGen) agents. Set an AGENTOPS_API_KEY in your environment and call agentops.init()

Camel AI 🐪

Track and analyze CAMEL agents with full observability. Set an AGENTOPS_API_KEY in your environment and initialize AgentOps to get started.

Camel AI - Advanced agent communication framework
AgentOps integration example
Official Camel AI documentation

<details> <summary>Installation</summary>

bash
pip install "camel-ai[all]==0.2.11"
pip install agentops

python
import os
import agentops
from camel.agents import ChatAgent
from camel.messages import BaseMessage
from camel.models import ModelFactory
from camel.types import ModelPlatformType, ModelType

# Initialize AgentOps
agentops.init(os.getenv("AGENTOPS_API_KEY"), tags=["CAMEL Example"])

# Import toolkits after AgentOps init for tracking
from camel.toolkits import SearchToolkit

# Set up the agent with search tools
sys_msg = BaseMessage.make_assistant_message(
    role_name='Tools calling operator',
    content='You are a helpful assistant'
)

# Configure tools and model
tools = [*SearchToolkit().get_tools()]
model = ModelFactory.create(
    model_platform=ModelPlatformType.OPENAI,
    model_type=ModelType.GPT_4O_MINI,
)

# Create and run the agent
camel_agent = ChatAgent(
    system_message=sys_msg,
    model=model,
    tools=tools,
)

response = camel_agent.step("What is AgentOps?")
print(response)

agentops.end_session("Success")

Check out our Camel integration guide for more examples including multi-agent scenarios.

</details>

Langchain 🦜🔗

AgentOps works seamlessly with applications built using Langchain. To use the handler, install Langchain as an optional dependency:

<details> <summary>Installation</summary>

shell
pip install agentops[langchain]

To use the handler, import and set

python
import os
from langchain.chat_models import ChatOpenAI
from langchain.agents import initialize_agent, AgentType
from agentops.integration.callbacks.langchain import LangchainCallbackHandler

AGENTOPS_API_KEY = os.environ['AGENTOPS_API_KEY']
handler = LangchainCallbackHandler(api_key=AGENTOPS_API_KEY, tags=['Langchain Example'])

llm = ChatOpenAI(openai_api_key=OPENAI_API_KEY,
                 callbacks=[handler],
                 model='gpt-3.5-turbo')

agent = initialize_agent(tools,
                         llm,
                         agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION,
                         verbose=True,
                         callbacks=[handler], # You must pass in a callback handler to record your agent
                         handle_parsing_errors=True)

Check out the Langchain Examples Notebook for more details including Async handlers.

</details>

Cohere ⌨️

First class support for Cohere(>=5.4.0). This is a living integration, should you need any added functionality please message us on Discord!

<details> <summary>Installation</summary>

bash
pip install cohere

python
import cohere
import agentops

# Beginning of program's code (i.e. main.py, __init__.py)
agentops.init(<INSERT YOUR API KEY HERE>)
co = cohere.Client()

chat = co.chat(
    message="Is it pronounced ceaux-hear or co-hehray?"
)

print(chat)

agentops.end_session('Success')

python
import cohere
import agentops

# Beginning of program's code (i.e. main.py, __init__.py)
agentops.init(<INSERT YOUR API KEY HERE>)

co = cohere.Client()

stream = co.chat_stream(
    message="Write me a haiku about the synergies between Cohere and AgentOps"
)

for event in stream:
    if event.event_type == "text-generation":
        print(event.text, end='')

agentops.end_session('Success')

</details>

Anthropic ﹨

Track agents built with the Anthropic Python SDK (>=0.32.0).

<details> <summary>Installation</summary>

bash
pip install anthropic

python
import anthropic
import agentops

# Beginning of program's code (i.e. main.py, __init__.py)
agentops.init(<INSERT YOUR API KEY HERE>)

client = anthropic.Anthropic(
    # This is the default and can be omitted
    api_key=os.environ.get("ANTHROPIC_API_KEY"),
)

message = client.messages.create(
        max_tokens=1024,
        messages=[
            {
                "role": "user",
                "content": "Tell me a cool fact about AgentOps",
            }
        ],
        model="claude-3-opus-20240229",
    )
print(message.content)

agentops.end_session('Success')

Streaming

python
import anthropic
import agentops

# Beginning of program's code (i.e. main.py, __init__.py)
agentops.init(<INSERT YOUR API KEY HERE>)

client = anthropic.Anthropic(
    # This is the default and can be omitted
    api_key=os.environ.get("ANTHROPIC_API_KEY"),
)

stream = client.messages.create(
    max_tokens=1024,
    model="claude-3-opus-20240229",
    messages=[
        {
            "role": "user",
            "content": "Tell me something cool about streaming agents",
        }
    ],
    stream=True,
)

response = ""
for event in stream:
    if event.type == "content_block_delta":
        response += event.delta.text
    elif event.type == "message_stop":
        print("\n")
        print(response)
        print("\n")

Async

python
import asyncio
from anthropic import AsyncAnthropic

client = AsyncAnthropic(
    # This is the default and can be omitted
    api_key=os.environ.get("ANTHROPIC_API_KEY"),
)


async def main() -> None:
    message = await client.messages.create(
        max_tokens=1024,
        messages=[
            {
                "role": "user",
                "content": "Tell me something interesting about async agents",
            }
        ],
        model="claude-3-opus-20240229",
    )
    print(message.content)


await main()

</details>

Mistral 〽️

Track agents built with the Mistral Python SDK (>=0.32.0).

<details> <summary>Installation</summary>

bash
pip install mistralai

Sync

python
from mistralai import Mistral
import agentops

# Beginning of program's code (i.e. main.py, __init__.py)
agentops.init(<INSERT YOUR API KEY HERE>)

client = Mistral(
    # This is the default and can be omitted
    api_key=os.environ.get("MISTRAL_API_KEY"),
)

message = client.chat.complete(
        messages=[
            {
                "role": "user",
                "content": "Tell me a cool fact about AgentOps",
            }
        ],
        model="open-mistral-nemo",
    )
print(message.choices[0].message.content)

agentops.end_session('Success')

Streaming

python
from mistralai import Mistral
import agentops

# Beginning of program's code (i.e. main.py, __init__.py)
agentops.init(<INSERT YOUR API KEY HERE>)

client = Mistral(
    # This is the default and can be omitted
    api_key=os.environ.get("MISTRAL_API_KEY"),
)

message = client.chat.stream(
        messages=[
            {
                "role": "user",
                "content": "Tell me something cool about streaming agents",
            }
        ],
        model="open-mistral-nemo",
    )

response = ""
for event in message:
    if event.data.choices[0].finish_reason == "stop":
        print("\n")
        print(response)
        print("\n")
    else:
        response += event.text

agentops.end_session('Success')

Async

python
import asyncio
from mistralai import Mistral

client = Mistral(
    # This is the default and can be omitted
    api_key=os.environ.get("MISTRAL_API_KEY"),
)


async def main() -> None:
    message = await client.chat.complete_async(
        messages=[
            {
                "role": "user",
                "content": "Tell me something interesting about async agents",
            }
        ],
        model="open-mistral-nemo",
    )
    print(message.choices[0].message.content)


await main()

Async Streaming

python
import asyncio
from mistralai import Mistral

client = Mistral(
    # This is the default and can be omitted
    api_key=os.environ.get("MISTRAL_API_KEY"),
)


async def main() -> None:
    message = await client.chat.stream_async(
        messages=[
            {
                "role": "user",
                "content": "Tell me something interesting about async streaming agents",
            }
        ],
        model="open-mistral-nemo",
    )

    response = ""
    async for event in message:
        if event.data.choices[0].finish_reason == "stop":
            print("\n")
            print(response)
            print("\n")
        else:
            response += event.text


await main()

</details>

CamelAI ﹨

Track agents built with the CamelAI Python SDK (>=0.32.0).

<details> <summary>Installation</summary>

bash
pip install camel-ai[all]
pip install agentops

python
#Import Dependencies
import agentops
import os
from getpass import getpass
from dotenv import load_dotenv

#Set Keys
load_dotenv()
openai_api_key = os.getenv("OPENAI_API_KEY") or "<your openai key here>"
agentops_api_key = os.getenv("AGENTOPS_API_KEY") or "<your agentops key here>"

</details>

You can find usage examples here!.

LiteLLM 🚅

AgentOps provides support for LiteLLM(>=1.3.1), allowing you to call 100+ LLMs using the same Input/Output Format.

<details> <summary>Installation</summary>

bash
pip install litellm

python
# Do not use LiteLLM like this
# from litellm import completion
# ...
# response = completion(model="claude-3", messages=messages)

# Use LiteLLM like this
import litellm
...
response = litellm.completion(model="claude-3", messages=messages)
# or
response = await litellm.acompletion(model="claude-3", messages=messages)

</details>

LlamaIndex 🦙

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

<details> <summary>Installation</summary>

shell
pip install llama-index-instrumentation-agentops

To use the handler, import and set

python
from llama_index.core import set_global_handler

# NOTE: Feel free to set your AgentOps environment variables (e.g., 'AGENTOPS_API_KEY')
# as outlined in the AgentOps documentation, or pass the equivalent keyword arguments
# anticipated by AgentOps' AOClient as **eval_params in set_global_handler.

set_global_handler("agentops")

Check out the LlamaIndex docs for more details.

</details>

Llama Stack 🦙🥞

AgentOps provides support for Llama Stack Python Client(>=0.0.53), allowing you to monitor your Agentic applications.

SwarmZero AI 🐝

Track and analyze SwarmZero agents with full observability. Set an AGENTOPS_API_KEY in your environment and initialize AgentOps to get started.

SwarmZero - Advanced multi-agent framework
AgentOps integration example
SwarmZero AI integration example
SwarmZero AI - AgentOps documentation
Official SwarmZero Python SDK

<details> <summary>Installation</summary>

bash
pip install swarmzero
pip install agentops

python
from dotenv import load_dotenv
load_dotenv()

import agentops
agentops.init(<INSERT YOUR API KEY HERE>)

from swarmzero import Agent, Swarm
# ...

</details>

Evaluations Roadmap 🧭

Platform	Dashboard	Evals
✅ Python SDK	✅ Multi-session and Cross-session metrics	✅ Custom eval metrics
🚧 Evaluation builder API	✅ Custom event tag tracking	🔜 Agent scorecards
🚧 Javascript/Typescript SDK (Alpha)	✅ Session replays	🔜 Evaluation playground + leaderboard

Debugging Roadmap 🧭

Performance testing	Environments	LLM Testing	Reasoning and execution testing
✅ Event latency analysis	🔜 Non-stationary environment testing	🔜 LLM non-deterministic function detection	🚧 Infinite loops and recursive thought detection
✅ Agent workflow execution pricing	🔜 Multi-modal environments	🚧 Token limit overflow flags	🔜 Faulty reasoning detection
🚧 Success validators (external)	🔜 Execution containers	🔜 Context limit overflow flags	🔜 Generative code validators
🔜 Agent controllers/skill tests	✅ Honeypot and prompt injection detection (PromptArmor)	✅ API bill tracking	🔜 Error breakpoint analysis
🔜 Information context constraint testing	🔜 Anti-agent roadblocks (i.e. Captchas)	🔜 CI/CD integration checks
🔜 Regression testing	✅ Multi-agent framework visualization

Why AgentOps? 🤔

Without the right tools, AI agents are slow, expensive, and unreliable. Our mission is to bring your agent from prototype to production. Here's why AgentOps stands out:

Comprehensive Observability: Track your AI agents' performance, user interactions, and API usage.
Real-Time Monitoring: Get instant insights with session replays, metrics, and live monitoring tools.
Cost Control: Monitor and manage your spend on LLM and API calls.
Failure Detection: Quickly identify and respond to agent failures and multi-agent interaction issues.
Tool Usage Statistics: Understand how your agents utilize external tools with detailed analytics.
Session-Wide Metrics: Gain a holistic view of your agents' sessions with comprehensive statistics.

AgentOps is designed to make agent observability, testing, and monitoring easy.

Star History

Check out our growth in the community:

Popular projects using AgentOps

Repository	Stars
<img class="avatar mr-2" src="https://avatars.githubusercontent.com/u/2707039?s=40&v=4" width="20" height="20" alt=""> geekan / MetaGPT	42787
<img class="avatar mr-2" src="https://avatars.githubusercontent.com/u/130722866?s=40&v=4" width="20" height="20" alt=""> run-llama / llama_index	34446
<img class="avatar mr-2" src="https://avatars.githubusercontent.com/u/170677839?s=40&v=4" width="20" height="20" alt=""> crewAIInc / crewAI	18287
<img class="avatar mr-2" src="https://avatars.githubusercontent.com/u/134388954?s=40&v=4" width="20" height="20" alt=""> camel-ai / camel	5166
<img class="avatar mr-2" src="https://avatars.githubusercontent.com/u/152537519?s=40&v=4" width="20" height="20" alt=""> superagent-ai / superagent	5050
<img class="avatar mr-2" src="https://avatars.githubusercontent.com/u/30197649?s=40&v=4" width="20" height="20" alt=""> iyaja / llama-fs	4713
<img class="avatar mr-2" src="https://avatars.githubusercontent.com/u/188122941?s=40&v=4" width="20" height="20" alt=""> ag2ai / ag2	4240
<img class="avatar mr-2" src="https://avatars.githubusercontent.com/u/162546372?s=40&v=4" width="20" height="20" alt=""> BasedHardware / Omi	2723
<img class="avatar mr-2" src="https://avatars.githubusercontent.com/u/454862?s=40&v=4" width="20" height="20" alt=""> MervinPraison / PraisonAI	2007
<img class="avatar mr-2" src="https://avatars.githubusercontent.com/u/140554352?s=40&v=4" width="20" height="20" alt=""> AgentOps-AI / Jaiqu	272
<img class="avatar mr-2" src="https://avatars.githubusercontent.com/u/173542722?s=48&v=4" width="20" height="20" alt=""> swarmzero / swarmzero	195
<img class="avatar mr-2" src="https://avatars.githubusercontent.com/u/3074263?s=40&v=4" width="20" height="20" alt=""> strnad / CrewAI-Studio	134
<img class="avatar mr-2" src="https://avatars.githubusercontent.com/u/18406448?s=40&v=4" width="20" height="20" alt=""> alejandro-ao / exa-crewai	55
<img class="avatar mr-2" src="https://avatars.githubusercontent.com/u/64493665?s=40&v=4" width="20" height="20" alt=""> tonykipkemboi / youtube_yapper_trapper	47
<img class="avatar mr-2" src="https://avatars.githubusercontent.com/u/17598928?s=40&v=4" width="20" height="20" alt=""> sethcoast / cover-letter-builder	27
<img class="avatar mr-2" src="https://avatars.githubusercontent.com/u/109994880?s=40&v=4" width="20" height="20" alt=""> bhancockio / chatgpt4o-analysis	19
<img class="avatar mr-2" src="https://avatars.githubusercontent.com/u/14105911?s=40&v=4" width="20" height="20" alt=""> breakstring / Agentic_Story_Book_Workflow	14
<img class="avatar mr-2" src="https://avatars.githubusercontent.com/u/124134656?s=40&v=4" width="20" height="20" alt=""> MULTI-ON / multion-python	13