Metadata-Version: 2.4
Name: langgraph-viz
Version: 0.1.2
Summary: Real-time browser-based visualization for LangGraph workflows
Project-URL: Homepage, https://github.com/mk-tdev/langgraph-viz
Project-URL: Repository, https://github.com/mk-tdev/langgraph-viz
Project-URL: Documentation, https://github.com/mk-tdev/langgraph-viz#readme
Project-URL: Bug Tracker, https://github.com/mk-tdev/langgraph-viz/issues
Author-email: MK T Dev <codewithmkdev@gmail.com>
License: MIT
License-File: LICENSE
Keywords: agents,debugging,langchain,langgraph,llm,state-machine,visualization,workflow
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
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
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development :: Debuggers
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.9
Requires-Dist: deepdiff>=6.7.0
Requires-Dist: fastapi>=0.104.0
Requires-Dist: langchain-anthropic>=0.3.22
Requires-Dist: langchain-openai>=0.3.35
Requires-Dist: langchain>=0.3.27
Requires-Dist: langgraph>=0.0.1
Requires-Dist: pydantic>=2.12.5
Requires-Dist: python-dotenv>=1.2.1
Requires-Dist: uvicorn[standard]>=0.24.0
Requires-Dist: websockets>=12.0
Provides-Extra: dev
Requires-Dist: black>=23.0.0; extra == 'dev'
Requires-Dist: pytest>=7.4.0; extra == 'dev'
Requires-Dist: ruff>=0.1.0; extra == 'dev'
Description-Content-Type: text/markdown

# LangGraph Viz

**Real-time browser-based visualization for LangGraph workflows.**

Debug and understand your LangGraph agents with live state inspection, graph visualization, and execution timeline.

![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)
![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)

## Features

- 🔴 **Live Graph Visualization** - See your workflow graph with real-time node highlighting
- 📊 **State Inspector** - View full state and diffs at each execution step
- ⏱️ **Event Timeline** - Scrub through execution history with playback controls
- 🔌 **Zero Config** - Works with any compiled LangGraph app
- 🚀 **Minimal Overhead** - Designed for development debugging

## Installation

```bash
pip install langgraph-viz
```

## Quick Start

```python
from langgraph_viz import visualize
from your_app import app  # Your compiled LangGraph

# Context manager style - auto opens browser
with visualize(app) as viz_app:
    result = viz_app.invoke({"query": "Hello world"})

# Or start server manually
viz = visualize(app, auto_open=False)
viz.server.start()
# ... run your app ...
viz.server.stop()
```

Open `http://localhost:8765` to see the visualization.

## How It Works

1. **Wrap your app** - `visualize()` wraps your LangGraph app to intercept execution events
2. **Start the server** - A FastAPI server streams events via WebSocket
3. **View in browser** - A React frontend renders the graph, timeline, and state

## Configuration

```python
visualize(
    app,
    port=8765,           # Server port (default: 8765)
    auto_open=True,      # Auto-open browser (default: True)
)
```

## Requirements

- Python 3.9+
- LangGraph >= 0.0.1
- A modern web browser

## Development

```bash
# Clone the repo
git clone https://github.com/yourusername/langgraph-viz.git
cd langgraph-viz

# Install dev dependencies
pip install -e ".[dev]"

# Build frontend (requires Node.js)
cd frontend && npm install && npm run build && cd ..

# Run tests
pytest
```

## License

MIT License - see [LICENSE](LICENSE) for details.
