Parmana
Proof of Human Authority in AI Systems
The official Python SDK for 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 verifiable execution evidence.
Why Parmana
Modern AI systems can:
- Plan
- Reason
- Call tools
- Invoke APIs
- Execute business workflows
However, most AI systems cannot answer critical governance questions:
- Who authorized this execution?
- Which policy approved it?
- Was the execution independently verified?
- Can the execution be replayed?
- Is there cryptographic evidence of what occurred?
Parmana provides the execution trust layer that answers these questions.
Installation
pip install parmana
Requirements
- Python 3.10 or later
- 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.models import BusinessTransaction
transaction = BusinessTransaction(
business_transaction_id="txn-001",
)
trust_record = client.execute(transaction)
print(trust_record.trust_record_id)
Verify an Execution
verification = client.verify("txn-001")
print(verification.status)
Replay an Execution
result = client.replay("txn-001")
print(result.success)
Execution Lifecycle
Business Transaction
|
v
Execution
|
v
Verification
|
v
Receipt
|
v
Execution Trust Record
Python SDK
| Method | Description |
|---|---|
health() |
Runtime health check |
execute() |
Execute a Business Transaction |
verify() |
Verify an execution |
replay() |
Deterministic replay |
receipt() |
Generate an execution receipt |
transaction() |
Retrieve a Business Transaction |
trust_record() |
Retrieve an Execution Trust Record |
validate_policy() |
Validate a policy definition |
Each of these is also available under its own namespace (e.g. client.execution.execute(), client.verification.verify(), client.replay.replay()) for finer-grained access to that API's other operations, such as client.verification.get_latest() or client.transactions.list().
Documentation
- Documentation: https://docs.parmana.ai
- GitHub: https://github.com/pavancharak/parmana-exp
- Issues: https://github.com/pavancharak/parmana-exp/issues
License
Apache License 2.0
Parmana
Proof of Human Authority in AI Systems
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file parmana-1.1.0.tar.gz.
File metadata
- Download URL: parmana-1.1.0.tar.gz
- Upload date:
- Size: 42.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.14.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d254c99841f6544ceb51102a3fbc50230b06a03cec3ac352cb699e7e477ea600
|
|
| MD5 |
d6e3cf6e3b3a565cb018a0a2d5c8fd09
|
|
| BLAKE2b-256 |
2205b06ea17821b97b54f10eb45cababdfcbf6808b49b6512ff678968e25b1da
|
File details
Details for the file parmana-1.1.0-py3-none-any.whl.
File metadata
- Download URL: parmana-1.1.0-py3-none-any.whl
- Upload date:
- Size: 41.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.14.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f99fb1236bf9d618e108d83b9d8e2859a751bd84867860af9eeeacbd55d2797f
|
|
| MD5 |
6188e1a91e6f775dfdcf4b0709df057b
|
|
| BLAKE2b-256 |
affac709cc2ccfe3b172460929793bbbc0a17362e902bcc2440d8251be8a277c
|