Metadata-Version: 2.4
Name: gangway
Version: 0.1.0
Summary: A smart Agent-to-Server Bridge connecting AI agents to remote environments as an MCP server and REST API.
Project-URL: Homepage, https://github.com/abdullahmansour/gangway
Author-email: Abdullah Mansour <abdullahmansour.marketing@gmail.com>
License: MIT
License-File: LICENSE
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
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: >=3.8
Description-Content-Type: text/markdown

# gangway

A smart Agent-to-Server Bridge connecting AI agents (like Cursor and Claude Desktop) to remote environments (Kaggle, Colab, VPS) for full control, functioning as both an MCP server and REST API.

## Features

* **Zero-Dependency Server**: Built using only Python standard library to prevent environment pollution or package conflicts on remote nodes.
* **Context Optimization Tools**: Optimized tools for AIs (e.g., `preview_file`, `project_overview`, fast search) to save context window tokens.
* **Background Job Control**: Execute and monitor long-running tasks asynchronously.
* **Zero-Config Tunneling**: Integrated Cloudflare Tunnel to bypass NAT / firewalls.
* **Directory State Management**: Keep track of the active working directory across execution contexts.

## Installation

```bash
pip install gangway
```
