agentauditai-sdk
On-chain EU AI Act compliance for AI agents — immutable audit logs, Know Your Agent (KYA) registration, incident reporting, and post-market monitoring across 5 EVM networks.
Enforcement deadline: August 2, 2026.
Installation
pip install agentauditai-sdk
Quick Start
1. Register an AI agent (Art. 13, 26 — KYA standard)
from agentauditai import AgentAuditClient
client = AgentAuditClient(
api_key="your-api-key",
base_url="https://your-agentaudit-api",
network="base",
)
registration = client.register_agent(
agent_id="42",
name="customer-support-agent",
model="claude-sonnet-4-6",
network="base",
)
print(f"Registered: tx={registration.tx_hash}")
print(f"Articles covered: {registration.articles}")
2. Audit an agent action (Art. 12, 19 — record-keeping)
from agentauditai import AgentAuditClient
client = AgentAuditClient(api_key="your-api-key", network="arbitrum")
result = client.audit_action(
agent_id="42",
action="LLM_DECISION",
data={
"prompt": "Summarise the customer complaint",
"response": "Refund approved for order #8821",
"model": "claude-sonnet-4-6",
},
risk_level="HIGH",
)
print(f"Logged on-chain: {result.tx_hash}")
print(f"Audit ID: {result.audit_id}")
print(f"Articles triggered: {result.articles}")
3. Get compliance report (Art. 72 — post-market monitoring)
from agentauditai import AgentAuditClient
client = AgentAuditClient(api_key="your-api-key", network="base")
# Risk score
risk = client.get_risk_score(agent_id="42")
print(f"Risk level: {risk.level} score: {risk.score}")
print(f"Status: {risk.compliance_status}")
# Full compliance report
report = client.get_compliance_report(agent_id="42")
print(f"Agent: {report.agent_name}")
print(f"Total actions logged: {report.total_actions_logged}")
print(f"Applicable articles: {report.applicable_articles}")
print(f"Compliance status: {report.compliance_status}")
for obligation in report.obligations:
status = "PASS" if obligation["met"] else "FAIL"
print(f" [{status}] {obligation['article']} — {obligation['obligation']}")
EU AI Act Coverage
| Article | Obligation | Method |
|---|---|---|
| Art. 9 | Risk management system | get_risk_score() |
| Art. 11 | Technical documentation | register_agent() |
| Art. 12 | Record-keeping & audit logs | audit_action() |
| Art. 13 | Transparency to users | register_agent() |
| Art. 14 | Human oversight | audit_action() with action tagging |
| Art. 19 | Conformity assessment logging | audit_action() |
| Art. 26 | Deployer obligations (KYA) | register_agent() |
| Art. 72 | Post-market monitoring | get_compliance_report() |
| Art. 73 | Serious incident reporting | audit_action(action="REPORT_INCIDENT") |
Supported Networks
| Network | Chain ID |
|---|---|
| Base Mainnet | 8453 |
| Arbitrum One | 42161 |
| Optimism Mainnet | 10 |
| Polygon Mainnet | 137 |
| Mantle Mainnet | 5000 |
Configuration
| Parameter | Environment Variable | Default |
|---|---|---|
api_key |
AGENTAUDIT_API_KEY |
— |
base_url |
— | http://localhost:3000 |
network |
— | base |
timeout |
— | 30 |
Links
- Website: getagentaudit.xyz
- PyPI: pypi.org/project/agentauditai-sdk
- npm: npmjs.com/package/@agentauditai/sdk
AgentAudit AI — a RunLockAI product
Metadata
Release files for agentauditai-sdk 1.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agentauditai_sdk-1.0.0.tar.gz | 5.6 kB | Without provenance | Details for agentauditai_sdk-1.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentauditai_sdk-1.0.0-py3-none-any.whl | Python 3 | none | any | Details for agentauditai_sdk-1.0.0-py3-none-any.whl |
Total release size: 11.9 kB
Release files / agentauditai_sdk-1.0.0.tar.gz
| Download URL | agentauditai_sdk-1.0.0.tar.gz |
|---|---|
| Size | 5.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f188b71391a6a33c6aec5b17c8b44fc334329f63655520cf770b2fc855a4d8a4
|
|
BLAKE2b-256 checksum How to use checksums |
253e5c88d17fde17c1babd7f0890a1f21900db4cc1f2fa5b4648f3f4cc844681
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.1
|
Release files / agentauditai_sdk-1.0.0-py3-none-any.whl
| Download URL | agentauditai_sdk-1.0.0-py3-none-any.whl |
|---|---|
| Size | 6.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
07e5adf345534a245c405d4325d5e88d46e7e5519f33b009e447f09ff4d40318
|
|
BLAKE2b-256 checksum How to use checksums |
f3ef6bd29591d20d078a43a85d87548d7309b575e712a0022caf4df56350d9f3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.1
|
Security for agentauditai-sdk 1.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.