# 🔒 Skyrelis: AI Agent Security Library
**Enterprise-grade security for AI agents, starting with comprehensive observability.**
[](https://badge.fury.io/py/skyrelis)
[](https://www.python.org/downloads/)
[](https://github.com/skyrelis/skyrelis/blob/main/LICENSE)
[](https://skyrelis.com)
---
## 🛡️ **Why Agent Security Matters**
As AI agents become more powerful and autonomous, they present new security challenges:
- **Prompt Injection Attacks**: Malicious inputs that hijack agent behavior
- **Data Exposure**: Agents accessing sensitive information inappropriately
- **Uncontrolled Actions**: Agents performing unintended or harmful operations
- **Compliance Risks**: Lack of audit trails for regulated industries
**Skyrelis provides the security foundation your AI agents need.**
---
## ✨ Current Security Features (v1.0)
🔍 **Complete Observability** - Full visibility into agent execution and decision-making
🎯 **System Prompt Security** - Monitor and protect agent instructions and behaviors
📊 **Real-time Monitoring** - Instant alerts for suspicious agent activities
🏷️ **Agent Registry** - Centralized inventory and security posture management
🔗 **Zero-Config Integration** - Add security with just a decorator
⚡ **Production Ready** - Built for enterprise scale and reliability
🌐 **Standards Compliant** - OpenTelemetry, audit logging, and compliance ready
## 🚧 Coming Soon (Roadmap)
🛡️ **Prompt Injection Detection** - AI-powered input validation and threat detection
🏗️ **Agent Sandboxing** - Isolated execution environments with controlled permissions
👥 **Access Control & RBAC** - Role-based permissions for agent operations
🧠 **Behavioral Analysis** - ML-based anomaly detection for agent activities
📋 **Compliance Frameworks** - SOC2, GDPR, HIPAA compliance tools
🔐 **Secret Management** - Secure handling of API keys and sensitive data
---
## 🚀 Quick Start
### Installation
```bash
pip install skyrelis
```
### Secure Your Agent in 30 Seconds
Transform any LangChain agent into a security-monitored agent with one decorator:
```python
from skyrelis import observe
from langchain.agents import AgentExecutor, create_openai_functions_agent
from langchain_openai import ChatOpenAI
from langchain.prompts import ChatPromptTemplate
# Your normal LangChain agent setup
prompt = ChatPromptTemplate.from_messages([
("system", "You are a helpful AI assistant. Use tools when needed."),
("human", "{input}"),
("placeholder", "{agent_scratchpad}")
])
llm = ChatOpenAI(model="gpt-4o-mini")
agent = create_openai_functions_agent(llm, tools, prompt)
# Add enterprise security monitoring with one decorator! 🔒
@observe(remote_observer_url="https://your-security-monitor.com")
class SecureAgent(AgentExecutor):
pass
# Initialize and use - now with full security monitoring
secure_agent = SecureAgent(agent=agent, tools=tools)
result = secure_agent.invoke({"input": "What's the weather like?"})
# Your agent now has:
# ✅ Complete execution tracing
# ✅ System prompt monitoring
# ✅ Real-time security alerts
# ✅ Audit trail compliance
# ✅ Agent behavior analysis
```
## 🔒 What Security Data Gets Captured
When you add the `@observe` decorator, Skyrelis automatically captures security-relevant data:
### 🤖 **Agent Security Profile**
- **System Prompts**: Complete instructions given to the agent
- **Tool Access**: What tools the agent can use and how
- **LLM Configuration**: Model settings, temperature, safety filters
- **Permission Scope**: What the agent is authorized to do
### 📊 **Execution Security Logs**
- **Input Validation**: All user inputs and their sources
- **Tool Invocations**: Every tool call with parameters and results
- **LLM Interactions**: Complete conversation logs with the language model
- **Output Analysis**: All agent responses and actions taken
- **Error Tracking**: Security-relevant errors and failures
### 🚨 **Security Events**
- **Unusual Behavior**: Deviations from expected agent patterns
- **Failed Operations**: Blocked or failed actions that might indicate attacks
- **Access Attempts**: Unauthorized access attempts to tools or data
- **Performance Anomalies**: Unusual response times or resource usage
### 📋 **Compliance & Audit**
- **Complete Audit Trail**: Every action with timestamps and context
- **User Attribution**: Who triggered each agent interaction
- **Data Access Logs**: What data was accessed or modified
- **Retention Management**: Automated log retention per compliance requirements
---
## 🎛️ Security Configuration
### Basic Security Setup
```python
@observe(
monitor_url="https://your-security-monitor.com",
agent_name="customer_service_agent",
security_level="production", # "development", "staging", "production"
)
class CustomerServiceAgent(AgentExecutor):
pass
```
### Advanced Security Configuration
```python
@observe(
monitor_url="https://your-security-monitor.com",
agent_name="financial_advisor_agent",
security_level="production",
enable_audit_logging=True, # Full audit trail
enable_anomaly_detection=True, # Behavioral analysis (coming soon)
enable_input_validation=True, # Prompt injection detection (coming soon)
compliance_mode="SOC2", # Compliance framework (coming soon)
alert_thresholds={ # Security alerting
"unusual_tool_usage": 0.8,
"response_time_anomaly": 2.0,
"error_rate_spike": 0.1
}
)
class FinancialAdvisorAgent(AgentExecutor):
pass
```
### Environment-Based Security
```bash
# Security monitoring endpoints
export SKYRELIS_MONITOR_URL="https://your-security-monitor.com"
export SKYRELIS_SECURITY_LEVEL="production"
# Compliance and audit
export SKYRELIS_AUDIT_RETENTION_DAYS="2555" # 7 years for financial compliance
export SKYRELIS_COMPLIANCE_MODE="SOC2"
# Alert destinations
export SKYRELIS_SLACK_WEBHOOK="https://hooks.slack.com/..."
export SKYRELIS_SECURITY_EMAIL="security-team@company.com"
```
---
## 🔧 Security Integration Examples
### High-Security Financial Agent
```python
from skyrelis import observe
from langchain.agents import create_openai_functions_agent
from langchain_openai import ChatOpenAI
from langchain.tools import StructuredTool
def get_account_balance(account_id: str) -> str:
# This tool access is now fully monitored and audited
return f"Account {account_id}: $10,000"
@observe(
monitor_url="https://security.bank.com/monitor",
security_level="production",
compliance_mode="SOX",
enable_audit_logging=True
)
class BankingAgent(AgentExecutor):
pass
# Every interaction is now compliance-ready and security-monitored
```
### Customer Service with Threat Detection
```python
@observe(
monitor_url="https://security.company.com/monitor",
enable_anomaly_detection=True, # Detect unusual customer behavior
enable_input_validation=True, # Block prompt injection attempts
alert_on_threats=True # Real-time security alerts
)
class CustomerServiceAgent(AgentExecutor):
pass
# Agent automatically detects and blocks security threats
```
### Research Agent with Data Protection
```python
@observe(
monitor_url="https://security.research.com/monitor",
data_classification="confidential",
enable_data_loss_prevention=True, # Prevent sensitive data exposure
audit_data_access=True # Log all data access events
)
class ResearchAgent(AgentExecutor):
pass
# Complete data protection and access monitoring
```
---
## 📊 Security Monitoring Dashboard
The Skyrelis Security Monitor provides:
### 🚨 **Real-time Security Alerts**
- **Threat Detection**: Immediate alerts for security events
- **Anomaly Notifications**: Unusual agent behavior alerts
- **Compliance Violations**: Regulatory compliance failures
- **Performance Issues**: Security-impacting performance problems
### 📈 **Security Analytics**
- **Agent Risk Scores**: Security posture assessment for each agent
- **Threat Landscape**: Attack patterns and security trends
- **Compliance Reporting**: Automated compliance status reports
- **Incident Response**: Security event investigation tools
### 🔍 **Agent Security Inventory**
- **Security Profiles**: All agents with their security configurations
- **Permission Mapping**: What each agent can access and do
- **Vulnerability Assessment**: Security weaknesses and recommendations
- **Policy Compliance**: Adherence to security policies
### 📋 **Audit & Compliance**
- **Complete Audit Trail**: Every action logged for compliance
- **Regulatory Reports**: SOC2, GDPR, HIPAA compliance reporting
- **Data Lineage**: Track data flow through agent operations
- **Retention Management**: Automated compliance-based data retention
---
## 🏗️ Security Architecture
Skyrelis Security Architecture:
1. **Security Decorator**: Wraps agents with security monitoring
2. **Agent Registry**: Centralizes agent security profiles and policies
3. **Real-time Monitoring**: Captures all security-relevant events
4. **Threat Detection**: AI-powered security analysis (coming soon)
5. **Compliance Engine**: Automated compliance and audit reporting
6. **Alert System**: Real-time security notifications and incident response
All security monitoring happens transparently - your agent code remains unchanged while gaining enterprise-grade security!
---
## 📦 Installation Options
```bash
# Basic security monitoring
pip install skyrelis
# With advanced security features (coming soon)
pip install skyrelis[security]
# With compliance reporting
pip install skyrelis[compliance]
# With threat detection (coming soon)
pip install skyrelis[threat-detection]
# Everything
pip install skyrelis[all]
```
---
## 🎯 Why Choose Skyrelis?
### **For Security Teams**
- **Zero Agent Code Changes**: Add security without disrupting development
- **Complete Visibility**: See everything your agents are doing
- **Compliance Ready**: Built-in support for major compliance frameworks
- **Threat Detection**: AI-powered security monitoring
### **For Development Teams**
- **One-Line Integration**: Just add a decorator
- **No Performance Impact**: Lightweight, async monitoring
- **Development Friendly**: Rich debugging and troubleshooting tools
- **Production Ready**: Battle-tested at enterprise scale
### **For Compliance Officers**
- **Automated Audit Trails**: Complete logging without manual work
- **Regulatory Support**: SOC2, GDPR, HIPAA, SOX compliance
- **Risk Assessment**: Continuous security posture monitoring
- **Incident Response**: Complete investigation capabilities
---
## 🤝 Contributing
We welcome contributions to make AI agents more secure! Please see our [Contributing Guide](CONTRIBUTING.md) for details.
## 📄 License & Commercial Use
**Skyrelis is proprietary software** - see the [LICENSE](LICENSE) file for details.
### 🏢 **Commercial Licensing**
- **Evaluation & Development**: Free for non-commercial evaluation and development
- **Commercial Use**: Requires a separate commercial license agreement
- **Enterprise**: Contact us for enterprise licensing and support
📧 **Licensing Inquiries**: [security@skyrelis.com](mailto:security@skyrelis.com)
### 🔒 **Why Proprietary?**
As an AI agent security platform, Skyrelis requires:
- **Enterprise Support**: Dedicated support for mission-critical security
- **Compliance Guarantees**: Legal assurances for regulated industries
- **Advanced Features**: Continuous development of cutting-edge security capabilities
- **Professional Services**: Security consulting and custom implementations
## 🆘 Support
- 📚 **Documentation**: [skyrelis.readthedocs.io](https://skyrelis.readthedocs.io)
- 🔒 **Security Issues**: [security@skyrelis.com](mailto:security@skyrelis.com)
- 🐛 **Bug Reports**: [GitHub Issues](https://github.com/skyrelis/skyrelis/issues)
- 💬 **Discussions**: [GitHub Discussions](https://github.com/skyrelis/skyrelis/discussions)
---
**Made with 🔒 by the Skyrelis Security Team**
*Skyrelis: Securing AI agents for the enterprise.*
Raw data
{
"_id": null,
"home_page": "https://github.com/skyrelis/skyrelis",
"name": "skyrelis",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": "Skyrelis Security Team <security@skyrelis.com>",
"keywords": "ai, agents, security, observability, monitoring, tracing, langchain, telemetry, analytics, debugging, performance, opentelemetry, compliance, audit, threat-detection, cybersecurity, enterprise, SOC2, GDPR, HIPAA, risk-management, governance",
"author": "Skyrelis Security Team",
"author_email": "Skyrelis Security Team <security@skyrelis.com>",
"download_url": "https://files.pythonhosted.org/packages/46/29/8b6f1cc0ac83101b98e46fafbfd436c8931ec478657a3ef17163149a6c73/skyrelis-0.1.1.tar.gz",
"platform": null,
"description": "# \ud83d\udd12 Skyrelis: AI Agent Security Library\n\n**Enterprise-grade security for AI agents, starting with comprehensive observability.**\n\n[](https://badge.fury.io/py/skyrelis)\n[](https://www.python.org/downloads/)\n[](https://github.com/skyrelis/skyrelis/blob/main/LICENSE)\n[](https://skyrelis.com)\n\n---\n\n## \ud83d\udee1\ufe0f **Why Agent Security Matters**\n\nAs AI agents become more powerful and autonomous, they present new security challenges:\n- **Prompt Injection Attacks**: Malicious inputs that hijack agent behavior\n- **Data Exposure**: Agents accessing sensitive information inappropriately \n- **Uncontrolled Actions**: Agents performing unintended or harmful operations\n- **Compliance Risks**: Lack of audit trails for regulated industries\n\n**Skyrelis provides the security foundation your AI agents need.**\n\n---\n\n## \u2728 Current Security Features (v1.0)\n\n\ud83d\udd0d **Complete Observability** - Full visibility into agent execution and decision-making \n\ud83c\udfaf **System Prompt Security** - Monitor and protect agent instructions and behaviors \n\ud83d\udcca **Real-time Monitoring** - Instant alerts for suspicious agent activities \n\ud83c\udff7\ufe0f **Agent Registry** - Centralized inventory and security posture management \n\ud83d\udd17 **Zero-Config Integration** - Add security with just a decorator \n\u26a1 **Production Ready** - Built for enterprise scale and reliability \n\ud83c\udf10 **Standards Compliant** - OpenTelemetry, audit logging, and compliance ready \n\n## \ud83d\udea7 Coming Soon (Roadmap)\n\n\ud83d\udee1\ufe0f **Prompt Injection Detection** - AI-powered input validation and threat detection \n\ud83c\udfd7\ufe0f **Agent Sandboxing** - Isolated execution environments with controlled permissions \n\ud83d\udc65 **Access Control & RBAC** - Role-based permissions for agent operations \n\ud83e\udde0 **Behavioral Analysis** - ML-based anomaly detection for agent activities \n\ud83d\udccb **Compliance Frameworks** - SOC2, GDPR, HIPAA compliance tools \n\ud83d\udd10 **Secret Management** - Secure handling of API keys and sensitive data \n\n---\n\n## \ud83d\ude80 Quick Start\n\n### Installation\n\n```bash\npip install skyrelis\n```\n\n### Secure Your Agent in 30 Seconds\n\nTransform any LangChain agent into a security-monitored agent with one decorator:\n\n```python\nfrom skyrelis import observe\nfrom langchain.agents import AgentExecutor, create_openai_functions_agent\nfrom langchain_openai import ChatOpenAI\nfrom langchain.prompts import ChatPromptTemplate\n\n# Your normal LangChain agent setup\nprompt = ChatPromptTemplate.from_messages([\n (\"system\", \"You are a helpful AI assistant. Use tools when needed.\"),\n (\"human\", \"{input}\"),\n (\"placeholder\", \"{agent_scratchpad}\")\n])\n\nllm = ChatOpenAI(model=\"gpt-4o-mini\")\nagent = create_openai_functions_agent(llm, tools, prompt)\n\n# Add enterprise security monitoring with one decorator! \ud83d\udd12\n@observe(remote_observer_url=\"https://your-security-monitor.com\")\nclass SecureAgent(AgentExecutor):\n pass\n\n# Initialize and use - now with full security monitoring\nsecure_agent = SecureAgent(agent=agent, tools=tools)\nresult = secure_agent.invoke({\"input\": \"What's the weather like?\"})\n\n# Your agent now has:\n# \u2705 Complete execution tracing\n# \u2705 System prompt monitoring \n# \u2705 Real-time security alerts\n# \u2705 Audit trail compliance\n# \u2705 Agent behavior analysis\n```\n\n## \ud83d\udd12 What Security Data Gets Captured\n\nWhen you add the `@observe` decorator, Skyrelis automatically captures security-relevant data:\n\n### \ud83e\udd16 **Agent Security Profile**\n- **System Prompts**: Complete instructions given to the agent\n- **Tool Access**: What tools the agent can use and how \n- **LLM Configuration**: Model settings, temperature, safety filters\n- **Permission Scope**: What the agent is authorized to do\n\n### \ud83d\udcca **Execution Security Logs** \n- **Input Validation**: All user inputs and their sources\n- **Tool Invocations**: Every tool call with parameters and results\n- **LLM Interactions**: Complete conversation logs with the language model\n- **Output Analysis**: All agent responses and actions taken\n- **Error Tracking**: Security-relevant errors and failures\n\n### \ud83d\udea8 **Security Events**\n- **Unusual Behavior**: Deviations from expected agent patterns\n- **Failed Operations**: Blocked or failed actions that might indicate attacks\n- **Access Attempts**: Unauthorized access attempts to tools or data\n- **Performance Anomalies**: Unusual response times or resource usage\n\n### \ud83d\udccb **Compliance & Audit**\n- **Complete Audit Trail**: Every action with timestamps and context\n- **User Attribution**: Who triggered each agent interaction\n- **Data Access Logs**: What data was accessed or modified\n- **Retention Management**: Automated log retention per compliance requirements\n\n---\n\n## \ud83c\udf9b\ufe0f Security Configuration\n\n### Basic Security Setup\n```python\n@observe(\n monitor_url=\"https://your-security-monitor.com\",\n agent_name=\"customer_service_agent\",\n security_level=\"production\", # \"development\", \"staging\", \"production\"\n)\nclass CustomerServiceAgent(AgentExecutor):\n pass\n```\n\n### Advanced Security Configuration\n```python\n@observe(\n monitor_url=\"https://your-security-monitor.com\",\n agent_name=\"financial_advisor_agent\",\n security_level=\"production\",\n enable_audit_logging=True, # Full audit trail\n enable_anomaly_detection=True, # Behavioral analysis (coming soon)\n enable_input_validation=True, # Prompt injection detection (coming soon)\n compliance_mode=\"SOC2\", # Compliance framework (coming soon)\n alert_thresholds={ # Security alerting\n \"unusual_tool_usage\": 0.8,\n \"response_time_anomaly\": 2.0,\n \"error_rate_spike\": 0.1\n }\n)\nclass FinancialAdvisorAgent(AgentExecutor):\n pass\n```\n\n### Environment-Based Security\n```bash\n# Security monitoring endpoints\nexport SKYRELIS_MONITOR_URL=\"https://your-security-monitor.com\"\nexport SKYRELIS_SECURITY_LEVEL=\"production\"\n\n# Compliance and audit\nexport SKYRELIS_AUDIT_RETENTION_DAYS=\"2555\" # 7 years for financial compliance\nexport SKYRELIS_COMPLIANCE_MODE=\"SOC2\"\n\n# Alert destinations\nexport SKYRELIS_SLACK_WEBHOOK=\"https://hooks.slack.com/...\"\nexport SKYRELIS_SECURITY_EMAIL=\"security-team@company.com\"\n```\n\n---\n\n## \ud83d\udd27 Security Integration Examples\n\n### High-Security Financial Agent\n```python\nfrom skyrelis import observe\nfrom langchain.agents import create_openai_functions_agent\nfrom langchain_openai import ChatOpenAI\nfrom langchain.tools import StructuredTool\n\ndef get_account_balance(account_id: str) -> str:\n # This tool access is now fully monitored and audited\n return f\"Account {account_id}: $10,000\"\n\n@observe(\n monitor_url=\"https://security.bank.com/monitor\",\n security_level=\"production\",\n compliance_mode=\"SOX\",\n enable_audit_logging=True\n)\nclass BankingAgent(AgentExecutor):\n pass\n\n# Every interaction is now compliance-ready and security-monitored\n```\n\n### Customer Service with Threat Detection\n```python\n@observe(\n monitor_url=\"https://security.company.com/monitor\",\n enable_anomaly_detection=True, # Detect unusual customer behavior\n enable_input_validation=True, # Block prompt injection attempts \n alert_on_threats=True # Real-time security alerts\n)\nclass CustomerServiceAgent(AgentExecutor):\n pass\n\n# Agent automatically detects and blocks security threats\n```\n\n### Research Agent with Data Protection\n```python\n@observe(\n monitor_url=\"https://security.research.com/monitor\",\n data_classification=\"confidential\",\n enable_data_loss_prevention=True, # Prevent sensitive data exposure\n audit_data_access=True # Log all data access events\n)\nclass ResearchAgent(AgentExecutor):\n pass\n\n# Complete data protection and access monitoring\n```\n\n---\n\n## \ud83d\udcca Security Monitoring Dashboard\n\nThe Skyrelis Security Monitor provides:\n\n### \ud83d\udea8 **Real-time Security Alerts**\n- **Threat Detection**: Immediate alerts for security events\n- **Anomaly Notifications**: Unusual agent behavior alerts \n- **Compliance Violations**: Regulatory compliance failures\n- **Performance Issues**: Security-impacting performance problems\n\n### \ud83d\udcc8 **Security Analytics**\n- **Agent Risk Scores**: Security posture assessment for each agent\n- **Threat Landscape**: Attack patterns and security trends\n- **Compliance Reporting**: Automated compliance status reports\n- **Incident Response**: Security event investigation tools\n\n### \ud83d\udd0d **Agent Security Inventory**\n- **Security Profiles**: All agents with their security configurations\n- **Permission Mapping**: What each agent can access and do\n- **Vulnerability Assessment**: Security weaknesses and recommendations\n- **Policy Compliance**: Adherence to security policies\n\n### \ud83d\udccb **Audit & Compliance**\n- **Complete Audit Trail**: Every action logged for compliance\n- **Regulatory Reports**: SOC2, GDPR, HIPAA compliance reporting\n- **Data Lineage**: Track data flow through agent operations\n- **Retention Management**: Automated compliance-based data retention\n\n---\n\n## \ud83c\udfd7\ufe0f Security Architecture\n\nSkyrelis Security Architecture:\n\n1. **Security Decorator**: Wraps agents with security monitoring\n2. **Agent Registry**: Centralizes agent security profiles and policies\n3. **Real-time Monitoring**: Captures all security-relevant events\n4. **Threat Detection**: AI-powered security analysis (coming soon)\n5. **Compliance Engine**: Automated compliance and audit reporting\n6. **Alert System**: Real-time security notifications and incident response\n\nAll security monitoring happens transparently - your agent code remains unchanged while gaining enterprise-grade security!\n\n---\n\n## \ud83d\udce6 Installation Options\n\n```bash\n# Basic security monitoring\npip install skyrelis\n\n# With advanced security features (coming soon)\npip install skyrelis[security]\n\n# With compliance reporting\npip install skyrelis[compliance]\n\n# With threat detection (coming soon) \npip install skyrelis[threat-detection]\n\n# Everything\npip install skyrelis[all]\n```\n\n---\n\n## \ud83c\udfaf Why Choose Skyrelis?\n\n### **For Security Teams**\n- **Zero Agent Code Changes**: Add security without disrupting development\n- **Complete Visibility**: See everything your agents are doing\n- **Compliance Ready**: Built-in support for major compliance frameworks\n- **Threat Detection**: AI-powered security monitoring\n\n### **For Development Teams** \n- **One-Line Integration**: Just add a decorator\n- **No Performance Impact**: Lightweight, async monitoring\n- **Development Friendly**: Rich debugging and troubleshooting tools\n- **Production Ready**: Battle-tested at enterprise scale\n\n### **For Compliance Officers**\n- **Automated Audit Trails**: Complete logging without manual work\n- **Regulatory Support**: SOC2, GDPR, HIPAA, SOX compliance\n- **Risk Assessment**: Continuous security posture monitoring\n- **Incident Response**: Complete investigation capabilities\n\n---\n\n## \ud83e\udd1d Contributing\n\nWe welcome contributions to make AI agents more secure! Please see our [Contributing Guide](CONTRIBUTING.md) for details.\n\n## \ud83d\udcc4 License & Commercial Use\n\n**Skyrelis is proprietary software** - see the [LICENSE](LICENSE) file for details.\n\n### \ud83c\udfe2 **Commercial Licensing**\n\n- **Evaluation & Development**: Free for non-commercial evaluation and development\n- **Commercial Use**: Requires a separate commercial license agreement\n- **Enterprise**: Contact us for enterprise licensing and support\n\n\ud83d\udce7 **Licensing Inquiries**: [security@skyrelis.com](mailto:security@skyrelis.com)\n\n### \ud83d\udd12 **Why Proprietary?**\n\nAs an AI agent security platform, Skyrelis requires:\n- **Enterprise Support**: Dedicated support for mission-critical security\n- **Compliance Guarantees**: Legal assurances for regulated industries \n- **Advanced Features**: Continuous development of cutting-edge security capabilities\n- **Professional Services**: Security consulting and custom implementations\n\n## \ud83c\udd98 Support\n\n- \ud83d\udcda **Documentation**: [skyrelis.readthedocs.io](https://skyrelis.readthedocs.io)\n- \ud83d\udd12 **Security Issues**: [security@skyrelis.com](mailto:security@skyrelis.com)\n- \ud83d\udc1b **Bug Reports**: [GitHub Issues](https://github.com/skyrelis/skyrelis/issues)\n- \ud83d\udcac **Discussions**: [GitHub Discussions](https://github.com/skyrelis/skyrelis/discussions)\n\n---\n\n**Made with \ud83d\udd12 by the Skyrelis Security Team**\n\n*Skyrelis: Securing AI agents for the enterprise.* \n",
"bugtrack_url": null,
"license": "Proprietary",
"summary": "AI Agent Security Library - Enterprise-grade security for AI agents, starting with comprehensive observability",
"version": "0.1.1",
"project_urls": {
"Bug Reports": "https://github.com/skyrelis/skyrelis/issues",
"Documentation": "https://skyrelis.readthedocs.io",
"Funding": "https://github.com/sponsors/skyrelis",
"Homepage": "https://github.com/skyrelis/skyrelis",
"Repository": "https://github.com/skyrelis/skyrelis",
"Security": "https://github.com/skyrelis/skyrelis/security"
},
"split_keywords": [
"ai",
" agents",
" security",
" observability",
" monitoring",
" tracing",
" langchain",
" telemetry",
" analytics",
" debugging",
" performance",
" opentelemetry",
" compliance",
" audit",
" threat-detection",
" cybersecurity",
" enterprise",
" soc2",
" gdpr",
" hipaa",
" risk-management",
" governance"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "aebd60f35f317c8b2361958187bcdc49483095de5015fc440ba2e7c69150be6b",
"md5": "f81eed6e1969d1279d647a15d8630a6d",
"sha256": "265e81fa1670d660e91e450f36c5bb44d813a61f759cebc080d45f79af3dce2e"
},
"downloads": -1,
"filename": "skyrelis-0.1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "f81eed6e1969d1279d647a15d8630a6d",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 29932,
"upload_time": "2025-07-27T03:32:31",
"upload_time_iso_8601": "2025-07-27T03:32:31.751881Z",
"url": "https://files.pythonhosted.org/packages/ae/bd/60f35f317c8b2361958187bcdc49483095de5015fc440ba2e7c69150be6b/skyrelis-0.1.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "46298b6f1cc0ac83101b98e46fafbfd436c8931ec478657a3ef17163149a6c73",
"md5": "c6fdaa5fd817601c6883dc6f54cc6dd2",
"sha256": "dbfda2cbc70f5d3153874332c5b5477c8cf304a7c4ed9ea0e1e49aef8813b0a5"
},
"downloads": -1,
"filename": "skyrelis-0.1.1.tar.gz",
"has_sig": false,
"md5_digest": "c6fdaa5fd817601c6883dc6f54cc6dd2",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 39687,
"upload_time": "2025-07-27T03:32:33",
"upload_time_iso_8601": "2025-07-27T03:32:33.216579Z",
"url": "https://files.pythonhosted.org/packages/46/29/8b6f1cc0ac83101b98e46fafbfd436c8931ec478657a3ef17163149a6c73/skyrelis-0.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-27 03:32:33",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "skyrelis",
"github_project": "skyrelis",
"github_not_found": true,
"lcname": "skyrelis"
}
JSON
