# AgentOps — Observability Dashboard for AI Agents

> Python SDK for monitoring AI agent sessions with real-time dashboards, token tracking, cost analysis, and error replay. Two lines of code to instrument any framework. 4,500+ GitHub stars.

## Install

Save as a script file and run:

## Quick Use

1. Install: `pip install agentops`
2. Add 2 lines to your agent code:

```python
import agentops
agentops.init("YOUR_API_KEY")  # Get free key at agentops.ai

# Your existing agent code works unchanged
# AgentOps auto-instruments OpenAI, Anthropic, LangChain, CrewAI, etc.
```

3. View sessions at [app.agentops.ai](https://app.agentops.ai)

---

## Intro

AgentOps is a Python observability SDK that gives you real-time dashboards, session replays, and cost tracking for AI agent applications with 4,500+ GitHub stars. Add two lines of code and get full visibility into every LLM call, tool use, and error your agents produce — across OpenAI, Anthropic, LangChain, CrewAI, AutoGen, and more. Best for teams running AI agents in production who need to debug failures and track costs. Works with: any Python AI framework. Setup time: under 1 minute.

---

## Core Features

### Auto-Instrumentation
AgentOps automatically detects and instruments popular frameworks:

```python
import agentops
agentops.init()

# These are automatically tracked:
from openai import OpenAI
from anthropic import Anthropic
from crewai import Agent, Task, Crew
```

Supported: OpenAI, Anthropic, LangChain, LlamaIndex, CrewAI, AutoGen, Cohere, Mistral, Groq, and more.

### Session Replay
Every agent run is recorded. View the complete timeline of LLM calls, tool invocations, errors, and custom events.

### Cost Tracking
Real-time token usage and cost breakdown by model, session, and user:

```python
agentops.init(tags=["production", "customer-support"])
```

### Error Analysis
Replay the exact sequence of events that led to any failure. Filter by error type, model, or time range.

### Custom Events

```python
agentops.record(agentops.ActionEvent(
    action_type="web_search",
    params={"query": "latest AI news"},
    returns="10 results found"
))
```

### Key Stats
- 4,500+ GitHub stars
- 15+ auto-instrumented frameworks
- Free tier: 1,000 sessions/month
- Real-time dashboard with <1s latency
- SOC 2 compliant

### FAQ

**Q: What is AgentOps?**
A: AgentOps is a Python observability SDK that provides real-time dashboards, session replays, and cost tracking for AI agent applications with just two lines of code.

**Q: Is AgentOps free?**
A: Yes, the SDK is open-source under MIT license. Free tier includes 1,000 sessions/month.

**Q: Does AgentOps work with Claude?**
A: Yes, AgentOps auto-instruments the Anthropic Python SDK. Every Claude API call is automatically tracked.

---

## Source & Thanks

> Created by [AgentOps-AI](https://github.com/AgentOps-AI). Licensed under MIT.
>
> [agentops](https://github.com/AgentOps-AI/agentops) — ⭐ 4,500+

Thanks to the AgentOps team for bringing production observability to AI agents.

---

<!-- ZH -->

## 快速使用

1. 安装: `pip install agentops`
2. 在 Agent 代码中添加 2 行:

```python
import agentops
agentops.init("YOUR_API_KEY")  # 在 agentops.ai 获取免费密钥
```

3. 在 [app.agentops.ai](https://app.agentops.ai) 查看实时面板

---

## 简介

AgentOps 是一个 Python 可观测性 SDK，为 AI Agent 应用提供实时仪表板、会话回放和成本追踪，GitHub 4,500+ stars。添加两行代码即可完整查看每个 LLM 调用和错误，支持 OpenAI、Anthropic、LangChain、CrewAI 等 15+ 框架。适合在生产环境运行 AI Agent 的团队。

---

## 来源与感谢

> Created by [AgentOps-AI](https://github.com/AgentOps-AI). Licensed under MIT.
>
> [agentops](https://github.com/AgentOps-AI/agentops) — ⭐ 4,500+

---
Source: https://tokrepo.com/en/workflows/3d040410-7f06-4ab6-aece-d6a0ef7325dd
Author: Agent Toolkit