ap3 1.0.0

Agent Privacy-Preserving Protocol - AP3

AP3 - Agent Privacy-Preserving Protocol

AP3 is a protocol for privacy-preserving computation between autonomous agents

What is AP3?

AP3 is designed to solve a critical challenge in the emerging agentic economy:
How can AI agents collaborate on sensitive computations while maintaining data confidentiality and competitive advantage?

Traditional agent communication requires data sharing, which creates risks:

• Competitive Intelligence Leakage: Proprietary algorithms, cost structures, and business strategies could be exposed
• Regulatory Compliance Issues: Data sharing may violate privacy regulations like GDPR and CCPA
• Trust Barriers: Parties are reluctant to collaborate without cryptographic privacy guarantees

AP3 addresses these challenges by providing a standardized framework for privacy-preserving computation using advanced cryptographic techniques.

As the agentic economy grows, AP3 will become essential infrastructure for trusted, privacy-preserving computation between autonomous agents, enabling a new generation of collaborative AI applications that respect data sovereignty and competitive advantage.

Examples

Example	Framework	Description
psi	Google ADK	Private Set Intersection for sanctions screening

See examples/psi/README.md for full setup, Docker, and UI instructions.

View Documentation

Install the docs dependencies and run mkdocs serve to view the documentation locally:

uv sync
uv pip install -r requirements-docs.txt
uv run mkdocs serve

Build the static site into site/:

uv run mkdocs build --clean

AP3 SDK

Key Docs:

• Installation Guide - Setup instructions
• Configuration - Environment setup
• Quick Start - First steps
• API Reference - Complete API docs
• Troubleshooting - Common issues

Features

• Private Set Intersection (PSI) - Check memberships without revealing sets
• Commitment System - Cryptographic data commitments
• Agent Integration - Works with Google ADK, A2A protocol
• Experimental proof fields - Result directives include placeholder OperationProofs fields for wiring/testing only (not cryptographic proofs yet)

Installation

Requires Python 3.11+.

uv sync && source .venv/bin/activate

Usage

Private Set Intersection

Note: PSI calls a native binary (libsanction_check_lib) bundled in packages/ap3-functions/ap3_functions/psi/binaries/. macOS (.dylib) and Linux (.so) are supported natively.

from ap3_functions import PSIOperation

initiator = PSIOperation()
receiver = PSIOperation()

sanction_list = ["Jane Smith,S001,456 Elm St", "Bob Brown,S002,789 Oak Ave"]

# Initiator starts the protocol
init_result = initiator.start(role="initiator", inputs={"customer_data": "John Doe,ID123,123 Main St"})
session_id = init_result["session_id"]

# Receiver processes msg1 against its sanction list
recv_result = receiver.receive(
    role="receiver",
    message=init_result["outgoing"],
    config={"sanction_list": sanction_list},
)

# Initiator processes msg2 and gets the result
final = initiator.process(session_id, recv_result["outgoing"])
is_match = final["result"]["is_match"]

🏗️ Architecture

ap3/
├── src/ap3/                          # Core SDK (publishes as `ap3`)
│   ├── types/                        # Pydantic models
│   ├── services/                     # Commitment & discovery services
│   ├── integrations/                 # LangChain, Google ADK adapters
│   └── crypto/                       # Cryptographic primitives
├── packages/
│   └── ap3-functions/                # Distribution: `ap3-functions`, import: `ap3_functions`
│       └── ap3_functions/            # Protocol implementations (FFI to Rust)
│           └── psi/                  # Private Set Intersection
└── examples/                         # Example agents
    └── psi_adk_simple/               # PSI sanctions screening with Google ADK

License

Licensed under the Apache License, Version 2.0. See LICENSE.