Metadata-Version: 2.4
Name: intelbridge-protocol
Version: 1.0.3
Summary: A Zero-Trust AI Agent Interoperability Protocol (AIP)
Home-page: https://github.com/shanbhuds/intelbridge-protocol
Author: Mr.Kiran B Nagargoje
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: pydantic>=2.0.0
Requires-Dist: python-dotenv>=1.0.0
Dynamic: author
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# 🌉 IntelBridge Protocol (AIP)

**Don't trap your AI agents in memory.** IntelBridge is a Zero-Trust Application-Layer Envelope Protocol for AI Agents. It allows agents to communicate securely across local Python processes, external API gateways, and message brokers (Kafka/Redis) without losing state or compromising security.

## 🚀 The Problem it Solves
Currently, AI frameworks (like LangGraph, AutoGen, or CrewAI) pass state as raw dictionaries in a single local process. If you want one agent in Python, another in Rust, and a third hosted on an external cloud, the local state breaks down. 

**IntelBridge solves this by decoupling the AI payload from the transport layer.**

## 🛡️ Features
* **Zero-Trust Validation:** All agent-to-agent messages are cryptographically signed using HMAC SHA-256.
* **Replay Attack Prevention:** Built-in TTL (Time-To-Live) and millisecond timestamps ensure stale or duplicate messages are rejected.
* **Deterministic Hashing:** Safely handles complex JSON payloads without crashing on dynamic objects like datetimes or UUIDs.
* **Transport Agnostic:** Send IntelBridge envelopes over HTTP webhooks, Redis PubSub, Kafka, or local LangGraph state.

## 📦 Quick Start

### 1. Installation
```bash
pip install intelbridge
