agentauditai-sdk 1.0.0__tar.gz

agentauditai_sdk-1.0.0/PKG-INFO

@@ -0,0 +1,164 @@
+Metadata-Version: 2.4
+Name: agentauditai-sdk
+Version: 1.0.0
+Summary: On-chain EU AI Act compliance SDK for AI agents — immutable audit logs, KYA registration, incident reporting, post-market monitoring.
+Author: agentauditAI
+License-Expression: MIT
+Project-URL: Homepage, https://getagentaudit.xyz
+Project-URL: Repository, https://github.com/agentauditAI/AgentAudit
+Project-URL: Bug Tracker, https://github.com/agentauditAI/AgentAudit/issues
+Project-URL: npm package, https://www.npmjs.com/package/@agentauditai/sdk
+Keywords: eu-ai-act,compliance,blockchain,audit,ai-agents,mantle,arbitrum,base,optimism,polygon
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Security
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: requests>=2.28.0
+
+# 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.**
+
+[![PyPI](https://img.shields.io/pypi/v/agentauditai-sdk)](https://pypi.org/project/agentauditai-sdk/)
+[![license](https://img.shields.io/pypi/l/agentauditai-sdk)](LICENSE)
+[![python](https://img.shields.io/pypi/pyversions/agentauditai-sdk)](https://pypi.org/project/agentauditai-sdk/)
+
+---
+
+## Installation
+
+```bash
+pip install agentauditai-sdk
+```
+
+---
+
+## Quick Start
+
+### 1. Register an AI agent (Art. 13, 26 — KYA standard)
+
+```python
+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)
+
+```python
+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)
+
+```python
+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](https://getagentaudit.xyz)
+- PyPI: [pypi.org/project/agentauditai-sdk](https://pypi.org/project/agentauditai-sdk/)
+- npm: [npmjs.com/package/@agentauditai/sdk](https://www.npmjs.com/package/@agentauditai/sdk)
+
+---
+
+AgentAudit AI — a [RunLockAI](https://getagentaudit.xyz) product

agentauditai_sdk-1.0.0/README.md

@@ -0,0 +1,140 @@
+# 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.**
+
+[![PyPI](https://img.shields.io/pypi/v/agentauditai-sdk)](https://pypi.org/project/agentauditai-sdk/)
+[![license](https://img.shields.io/pypi/l/agentauditai-sdk)](LICENSE)
+[![python](https://img.shields.io/pypi/pyversions/agentauditai-sdk)](https://pypi.org/project/agentauditai-sdk/)
+
+---
+
+## Installation
+
+```bash
+pip install agentauditai-sdk
+```
+
+---
+
+## Quick Start
+
+### 1. Register an AI agent (Art. 13, 26 — KYA standard)
+
+```python
+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)
+
+```python
+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)
+
+```python
+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](https://getagentaudit.xyz)
+- PyPI: [pypi.org/project/agentauditai-sdk](https://pypi.org/project/agentauditai-sdk/)
+- npm: [npmjs.com/package/@agentauditai/sdk](https://www.npmjs.com/package/@agentauditai/sdk)
+
+---
+
+AgentAudit AI — a [RunLockAI](https://getagentaudit.xyz) product

agentauditai_sdk-1.0.0/agentauditai/__init__.py

@@ -0,0 +1,12 @@
+from .client import AgentAuditClient, AgentAuditError
+from .models import AgentRegistration, AuditAction, ComplianceReport, RiskScore
+
+__version__ = "1.0.0"
+__all__ = [
+    "AgentAuditClient",
+    "AgentAuditError",
+    "AgentRegistration",
+    "AuditAction",
+    "ComplianceReport",
+    "RiskScore",
+]

agentauditai_sdk-1.0.0/agentauditai/client.py

@@ -0,0 +1,205 @@
+import hashlib
+import json
+import os
+from typing import Any, Dict, Literal, Optional
+
+import requests
+
+from .models import AgentRegistration, AuditAction, ComplianceReport, RiskScore
+
+Network = Literal["mantle", "base", "arbitrum", "optimism", "polygon"]
+RiskLevel = Literal["HIGH", "MEDIUM", "LOW"]
+
+NETWORKS = {
+    "mantle":   {"chain_id": 5000,  "explorer": "https://explorer.mantle.xyz"},
+    "base":     {"chain_id": 8453,  "explorer": "https://basescan.org"},
+    "arbitrum": {"chain_id": 42161, "explorer": "https://arbiscan.io"},
+    "optimism": {"chain_id": 10,    "explorer": "https://optimistic.etherscan.io"},
+    "polygon":  {"chain_id": 137,   "explorer": "https://polygonscan.com"},
+}
+
+
+class AgentAuditError(Exception):
+    """Raised when the AgentAudit API returns an error."""
+
+
+class AgentAuditClient:
+    """
+    Python client for the AgentAudit REST API.
+
+    Provides EU AI Act compliance for AI agents: immutable on-chain audit logs,
+    Know Your Agent (KYA) registration, risk scoring, and compliance reporting
+    across Mantle, Base, Arbitrum, Optimism, and Polygon.
+
+    Args:
+        api_key: Bearer token for the AgentAudit API. Falls back to
+            AGENTAUDIT_API_KEY environment variable.
+        base_url: Base URL of the AgentAudit API gateway (default: localhost:3000).
+        network: Default network for all operations.
+        timeout: HTTP request timeout in seconds.
+    """
+
+    def __init__(
+        self,
+        api_key: Optional[str] = None,
+        base_url: str = "http://localhost:3000",
+        network: Network = "base",
+        timeout: int = 30,
+    ) -> None:
+        self._api_key = api_key or os.environ.get("AGENTAUDIT_API_KEY", "")
+        self._base_url = base_url.rstrip("/")
+        self._network = network
+        self._timeout = timeout
+        self._session = requests.Session()
+        self._session.headers.update({
+            "Authorization": f"Bearer {self._api_key}",
+            "Content-Type": "application/json",
+        })
+
+    # ─── Internal ───
+
+    def _post(self, path: str, body: dict) -> dict:
+        resp = self._session.post(
+            f"{self._base_url}{path}", json=body, timeout=self._timeout
+        )
+        if not resp.ok:
+            raise AgentAuditError(f"API error {resp.status_code}: {resp.text}")
+        return resp.json()
+
+    def _get(self, path: str, params: Optional[dict] = None) -> dict:
+        resp = self._session.get(
+            f"{self._base_url}{path}", params=params, timeout=self._timeout
+        )
+        if not resp.ok:
+            raise AgentAuditError(f"API error {resp.status_code}: {resp.text}")
+        return resp.json()
+
+    # ─── Public API ───
+
+    @staticmethod
+    def hash_payload(data: Any) -> str:
+        """SHA-256 hash of a payload. Raw content never leaves your system."""
+        raw = json.dumps(data, sort_keys=True) if not isinstance(data, str) else data
+        return "sha256:" + hashlib.sha256(raw.encode()).hexdigest()
+
+    def register_agent(
+        self,
+        agent_id: str,
+        name: str,
+        model: str,
+        network: Optional[Network] = None,
+        risk_level: RiskLevel = "HIGH",
+    ) -> AgentRegistration:
+        """
+        Register an AI agent on-chain (Art. 13, 26 — KYA standard).
+
+        Writes an immutable REGISTER_AGENT record to the audit vault,
+        establishing the agent's identity and model on the selected network.
+        """
+        net = network or self._network
+        resp = self._post("/v1/audit", {
+            "agent_id": str(agent_id),
+            "action": "REGISTER_AGENT",
+            "decision": f"Agent '{name}' registered with model '{model}'",
+            "risk_level": risk_level,
+            "network": net,
+            "metadata": {"name": name, "model": model},
+        })
+        return AgentRegistration(
+            agent_id=str(agent_id),
+            name=name,
+            model=model,
+            network=net,
+            audit_id=resp.get("audit_id"),
+            tx_hash=resp.get("tx_hash"),
+            registered_at=resp.get("timestamp"),
+            articles=resp.get("articles", []),
+        )
+
+    def audit_action(
+        self,
+        agent_id: str,
+        action: str,
+        data: Dict[str, Any],
+        risk_level: RiskLevel = "HIGH",
+        network: Optional[Network] = None,
+    ) -> AuditAction:
+        """
+        Log an agent action on-chain (Art. 12, 19 — record-keeping).
+
+        The raw payload is hashed client-side; only the SHA-256 digest is
+        stored on-chain so sensitive data never touches the chain.
+        """
+        net = network or self._network
+        resp = self._post("/v1/audit", {
+            "agent_id": str(agent_id),
+            "action": action,
+            "decision": self.hash_payload(data),
+            "risk_level": risk_level,
+            "network": net,
+            "metadata": data,
+        })
+        return AuditAction(
+            audit_id=resp["audit_id"],
+            agent_id=str(agent_id),
+            action=action,
+            tx_hash=resp["tx_hash"],
+            network=net,
+            articles=resp.get("articles", []),
+            timestamp=resp["timestamp"],
+        )
+
+    def get_risk_score(
+        self,
+        agent_id: str,
+        network: Optional[Network] = None,
+    ) -> RiskScore:
+        """
+        Return the current risk score for an agent (Art. 9 — risk management).
+
+        Score is derived from the agent's on-chain compliance level:
+        high → 1.0, limited → 0.5, minimal → 0.2.
+        """
+        net = network or self._network
+        data = self._get(f"/v1/audit/{agent_id}/report", {"network": net})
+        compliance_level = data["agent"]["compliance_level"].upper()
+        score_map = {"HIGH": 1.0, "LIMITED": 0.5, "MINIMAL": 0.2}
+        return RiskScore(
+            agent_id=str(agent_id),
+            network=net,
+            level=compliance_level,
+            score=score_map.get(compliance_level, 0.5),
+            articles=data["eu_ai_act_compliance"]["applicable_articles"],
+            compliance_status=data["eu_ai_act_compliance"]["compliance_status"],
+        )
+
+    def get_compliance_report(
+        self,
+        agent_id: str,
+        network: Optional[Network] = None,
+    ) -> ComplianceReport:
+        """
+        Generate a full EU AI Act compliance report for an agent (Art. 72).
+
+        Pulls on-chain registration data and the full audit trail to produce
+        a structured report covering all applicable articles.
+        """
+        net = network or self._network
+        data = self._get(f"/v1/audit/{agent_id}/report", {"network": net})
+        agent = data["agent"]
+        summary = data["audit_summary"]
+        compliance = data["eu_ai_act_compliance"]
+        return ComplianceReport(
+            agent_id=str(agent_id),
+            network=net,
+            generated_at=data["generated_at"],
+            agent_name=agent["name"],
+            compliance_level=agent["compliance_level"],
+            active=agent["active"],
+            total_actions_logged=summary["total_actions_logged"],
+            first_action=summary.get("first_action"),
+            last_action=summary.get("last_action"),
+            applicable_articles=compliance["applicable_articles"],
+            compliance_status=compliance["compliance_status"],
+            obligations=compliance.get("obligations", []),
+        )

agentauditai_sdk-1.0.0/agentauditai/models.py

@@ -0,0 +1,51 @@
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Optional
+
+
+@dataclass
+class AgentRegistration:
+    agent_id: str
+    name: str
+    model: str
+    network: str
+    audit_id: Optional[str] = None
+    tx_hash: Optional[str] = None
+    registered_at: Optional[str] = None
+    articles: List[str] = field(default_factory=list)
+
+
+@dataclass
+class AuditAction:
+    audit_id: str
+    agent_id: str
+    action: str
+    tx_hash: str
+    network: str
+    articles: List[str]
+    timestamp: str
+
+
+@dataclass
+class RiskScore:
+    agent_id: str
+    network: str
+    level: str
+    score: float
+    articles: List[str]
+    compliance_status: str
+
+
+@dataclass
+class ComplianceReport:
+    agent_id: str
+    network: str
+    generated_at: str
+    agent_name: str
+    compliance_level: str
+    active: bool
+    total_actions_logged: int
+    first_action: Optional[str]
+    last_action: Optional[str]
+    applicable_articles: List[str]
+    compliance_status: str
+    obligations: List[Dict[str, Any]]

agentauditai_sdk-1.0.0/agentauditai_sdk.egg-info/PKG-INFO

@@ -0,0 +1,164 @@
+Metadata-Version: 2.4
+Name: agentauditai-sdk
+Version: 1.0.0
+Summary: On-chain EU AI Act compliance SDK for AI agents — immutable audit logs, KYA registration, incident reporting, post-market monitoring.
+Author: agentauditAI
+License-Expression: MIT
+Project-URL: Homepage, https://getagentaudit.xyz
+Project-URL: Repository, https://github.com/agentauditAI/AgentAudit
+Project-URL: Bug Tracker, https://github.com/agentauditAI/AgentAudit/issues
+Project-URL: npm package, https://www.npmjs.com/package/@agentauditai/sdk
+Keywords: eu-ai-act,compliance,blockchain,audit,ai-agents,mantle,arbitrum,base,optimism,polygon
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Security
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: requests>=2.28.0
+
+# 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.**
+
+[![PyPI](https://img.shields.io/pypi/v/agentauditai-sdk)](https://pypi.org/project/agentauditai-sdk/)
+[![license](https://img.shields.io/pypi/l/agentauditai-sdk)](LICENSE)
+[![python](https://img.shields.io/pypi/pyversions/agentauditai-sdk)](https://pypi.org/project/agentauditai-sdk/)
+
+---
+
+## Installation
+
+```bash
+pip install agentauditai-sdk
+```
+
+---
+
+## Quick Start
+
+### 1. Register an AI agent (Art. 13, 26 — KYA standard)
+
+```python
+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)
+
+```python
+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)
+
+```python
+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](https://getagentaudit.xyz)
+- PyPI: [pypi.org/project/agentauditai-sdk](https://pypi.org/project/agentauditai-sdk/)
+- npm: [npmjs.com/package/@agentauditai/sdk](https://www.npmjs.com/package/@agentauditai/sdk)
+
+---
+
+AgentAudit AI — a [RunLockAI](https://getagentaudit.xyz) product

agentauditai_sdk-1.0.0/agentauditai_sdk.egg-info/SOURCES.txt

@@ -0,0 +1,11 @@
+README.md
+pyproject.toml
+setup.py
+agentauditai/__init__.py
+agentauditai/client.py
+agentauditai/models.py
+agentauditai_sdk.egg-info/PKG-INFO
+agentauditai_sdk.egg-info/SOURCES.txt
+agentauditai_sdk.egg-info/dependency_links.txt
+agentauditai_sdk.egg-info/requires.txt
+agentauditai_sdk.egg-info/top_level.txt

agentauditai_sdk-1.0.0/agentauditai_sdk.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

agentauditai_sdk-1.0.0/agentauditai_sdk.egg-info/requires.txt

@@ -0,0 +1 @@
+requests>=2.28.0

agentauditai_sdk-1.0.0/agentauditai_sdk.egg-info/top_level.txt

@@ -0,0 +1 @@
+agentauditai

agentauditai_sdk-1.0.0/pyproject.toml

@@ -0,0 +1,35 @@
+[build-system]
+requires = ["setuptools>=61", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "agentauditai-sdk"
+version = "1.0.0"
+description = "On-chain EU AI Act compliance SDK for AI agents — immutable audit logs, KYA registration, incident reporting, post-market monitoring."
+readme = "README.md"
+license = "MIT"
+authors = [{name = "agentauditAI"}]
+keywords = [
+    "eu-ai-act", "compliance", "blockchain", "audit",
+    "ai-agents", "mantle", "arbitrum", "base", "optimism", "polygon",
+]
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Developers",
+
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Security",
+]
+requires-python = ">=3.9"
+dependencies = ["requests>=2.28.0"]
+
+[project.urls]
+Homepage = "https://getagentaudit.xyz"
+Repository = "https://github.com/agentauditAI/AgentAudit"
+"Bug Tracker" = "https://github.com/agentauditAI/AgentAudit/issues"
+"npm package" = "https://www.npmjs.com/package/@agentauditai/sdk"

agentauditai_sdk-1.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

agentauditai_sdk-1.0.0/setup.py

@@ -0,0 +1,3 @@
+from setuptools import setup
+
+setup()