Metadata-Version: 2.4
Name: nova-agentops
Version: 1.3.0
Summary: Professional observability SDK for AI Agents
Author-email: Terry <terry@example.com>
License: MIT
Project-URL: Homepage, https://github.com/Nova799/agent-ops-sdk
Keywords: ai,observability,agents,tracing,llm
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: httpx>=0.24.0
Requires-Dist: python-dotenv>=1.0.0
Provides-Extra: langchain
Requires-Dist: langchain-core>=0.2; extra == "langchain"
Provides-Extra: dev
Requires-Dist: pytest>=8; extra == "dev"
Requires-Dist: pytest-asyncio>=0.23; extra == "dev"

# 🚀 AgentOps SDK

**AgentOps** is a professional observability platform designed specifically for AI Agents. It acts as the "Chrome DevTools" for your LLM-powered applications, allowing you to monitor, debug, and optimize your agent's reasoning process in real-time.

## 🌟 Why AgentOps?

When building AI agents, the biggest challenge is the "Black Box" effect: you see the input and the output, but you don't know *why* the agent made a specific decision or where it got stuck.

AgentOps solves this by capturing:
- **The Internal Monologue**: See the exact reasoning (Thought) before an action.
- **Tool Execution**: Track exactly which tool was called and with what parameters.
- **State Snapshots**: Inspect the internal memory of your agent at any given step.
- **Visual Tracing**: A dynamic graph visualization of the agent's logic flow.

## 🛠️ Quick Start

### 1. Installation

You can install the SDK directly from this GitHub repository:

```bash
pip install git+https://github.com/Nova799/agent-ops-sdk.git
```

### 2. Configuration
Create a `.env` file in your project root:
```env
AGENT_OPS_API_KEY=your_secret_key
AGENT_OPS_URL=https://api.agentops.io
```

### 3. Basic Usage
```python
import asyncio
from agent_ops import AgentOps

ops = AgentOps()

async def main():
    # Context manager handles start/end automatically
    async with ops.trace(session_name="User Inquiry #123", metadata={"user": "alice"}):
        await ops.log_step(
            thought="The user is asking for the weather, I should use the weather tool",
            action="get_weather",
            observation="Sunny, 25°C",
            state_snapshot={"location": "Paris"},
        )

    # Automatic tracker
    @ops.track()
    async def my_tool(param):
        return f"Processed {param}"

    await ops.start_trace(session_name="tool run")
    await my_tool("hello")
    await ops.end_trace()

asyncio.run(main())
```

### 4. Inspect traces
```python
traces = await ops.list_traces(limit=10)
detail = await ops.get_trace(traces[0]["id"])
```

### 5. Sync client
```python
from agent_ops import AgentOpsSync
ops = AgentOpsSync()
ops.start_trace("demo")
ops.log_step(thought="hi")
ops.end_trace()
```

### 6. Sampling & redaction
```python
ops = AgentOps(sample_rate=0.1, redact_keys=["password", "token"])
```

## 📊 The Dashboard
Once integrated, open the AgentOps Dashboard to:
- **Visualize** the execution flow as an interactive node graph.
- **Inspect** detailed logs of every step.
- **Share** traces with your team for collaborative debugging.

---
© 2026 AgentOps Team. Built for the future of AI Agents.
