parmana 1.0.2

Official Python SDK for the Parmana Execution Trust Infrastructure.

# Parmana

**Proof of Human Authority in AI Systems**

[](https://pypi.org/project/parmana/)

[](https://pypi.org/project/parmana/)

[](LICENSE)

The official Python SDK for the **Parmana Execution Trust Infrastructure**.

Parmana enables organizations to confidently deploy AI in high-impact workflows by ensuring that **only authorized actions are executed** and every execution is accompanied by cryptographically verifiable evidence.

---

# Why Parmana?

Modern AI systems can:

- plan

- reason

- call tools

- invoke APIs

- execute business workflows

But most AI systems cannot answer fundamental governance questions:

- Who authorized this execution?

- Which policy approved it?

- Was the execution verified?

- Can it be replayed?

- Can it be independently audited?

- Can compliance teams prove what happened?

Parmana solves this problem.

---

# Core Principle

**AI can propose actions.**

**Parmana authorizes execution.**

Only Parmana-approved actions are executed.

---

# Features

- Human Authority

- Execution Authorization

- Policy Validation

- Business Transactions

- Verification

- Execution Trust Records

- Cryptographic Receipts

- Deterministic Replay

- Audit Evidence

- Python SDK

- REST API

- TypeScript SDK

---

# Installation

pip install parmana

---

# Requirements

- Python 3.10+

- Parmana Runtime

---

# Quick Start

from parmana import ParmanaClient



client = ParmanaClient(

    endpoint="http://localhost:3000",

)



print(client.version)

---

# Runtime Health

status = client.health()



print(status)

---

# Execute a Business Transaction

from parmana import ParmanaClient

from parmana.models import \*



client = ParmanaClient(

    endpoint="http://localhost:3000",

)



transaction = BusinessTransaction(

    ...

)



trust\_record = client.execute(transaction)



print(trust\_record.trust\_record\_id)

---

# Verify an Execution

verification = client.verify(

    business\_transaction\_id,

)



print(verification.status)

---

# Replay an Execution

result = client.replay(

    business\_transaction\_id,

)



print(result.success)

---

# Generate a Receipt

receipt = client.receipt(

    business\_transaction\_id,

)



print(receipt.receipt\_hash)

---

# Retrieve a Business Transaction

transaction = client.transaction(

    business\_transaction\_id,

)

---

# Retrieve an Execution Trust Record

trust\_record = client.trust\_record(

    business\_transaction\_id,

)

---

# Execution Lifecycle

Business Transaction

        │

        ▼

Execution

        │

        ▼

Verification

        │

        ▼

Receipt

        │

        ▼

Execution Trust Record

---

# Core Concepts

## Authority

Represents the human or system authority responsible for authorizing execution.

---

## Authorization

Represents permission granted by an Authority.

---

## Intent

Represents the requested business action.

---

## Policy

Represents the versioned policy evaluated by the Runtime.

---

## Business Transaction

The canonical execution request submitted to the Runtime.

---

## Decision

Policy evaluation result.

---

## Execution

Represents the performed execution.

---

## Verification

Independent verification produced by the Runtime.

---

## Receipt

Cryptographic proof of execution.

---

## Execution Trust Record

The canonical execution artifact containing:

- Business Transaction

- Executions

- Verifications

- Receipts

- Trust Hash

---

# Architecture

Application

      │

      ▼

 Python SDK

      │

 REST API

      │

 Parmana Runtime

      │

 ├── Policy Engine

 ├── Verification

 ├── Replay

 ├── Receipt

 ├── Storage

 └── Crypto

---

# Public APIs

The SDK provides:

| API | Purpose |

|------|----------|

| Health | Runtime health |

| Execute | Execute Business Transactions |

| Verify | Verify executions |

| Replay | Deterministic replay |

| Receipt | Generate receipts |

| Transaction | Retrieve Business Transactions |

| Trust Record | Retrieve Execution Trust Records |

| Policy | Validate policies |

---

# Error Handling

Example:

from parmana.errors import NetworkError



try:

    client.health()



except NetworkError:

    print("Runtime unavailable")

---

# Deterministic Replay

Replay enables independent verification that an execution can be reproduced using the recorded execution evidence.

Replay never changes execution history.

---

# Security

Parmana provides:

- Human authorization

- Versioned policies

- Cryptographic receipts

- Replayable execution

- Tamper-evident trust records

- Audit evidence

---

# Documentation

Documentation:

https://docs.parmana.ai

---

# Repository

GitHub:

https://github.com/pavancharak/parmana

---

# Issues

https://github.com/pavancharak/parmana/issues

---

# Contributing

Issues and pull requests are welcome.

Please ensure:

- Tests pass

- Documentation is updated

- Public APIs remain backward compatible

---

# License

Apache License 2.0

---

# Learn More

- Documentation

- Runtime

- REST API

- Python SDK

- TypeScript SDK

- Examples

- Architecture

- Verification

- Replay

- Execution Trust Records

---

**Parmana**

**Proof of Human Authority in AI Systems**