Open Agent Compliance Protocol

A governance layer for LangGraph that adds voting, consensus, and audit trails to multi-agent workflows. Transform your agent systems with democratic decision-making and adaptive prompting.

Quick Start

Get up and running with OACP in minutes. Installation, basic setup, and your first multi-agent system.

Get Started →

Examples

Explore real-world examples including research teams, game AI, content creation, and code review systems.

View Examples →

Core Concepts

Decorators →

Add OACP governance to functions with @with_oacp and wrap_node decorators.

Voting & Consensus →

Decision contracts, voting strategies, and consensus mechanisms for agent coordination.

Event Storage →

File, SQLite, and PostgreSQL storage backends for audit trails and event logging.

Key Features

Democratic Voting

Unanimous, majority, and weighted voting strategies for agent consensus decisions.

Adaptive Prompting

Learn from rejection feedback to automatically improve prompts and reduce consensus failures.

Audit Trails

Complete traceability with event logging, vote tracking, and governance compliance.

LangGraph Integration

Simple decorator-based integration with existing LangGraph workflows and nodes.

Installation

# Install from source
git clone https://github.com/Aaditya17032002/OACP.git
cd OACP
pip install -e .

Ready to start building? Check out our Quick Start Guide for detailed setup instructions or visit our GitHub repository.