Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI
Python agentagentopsagents-sdkaianthropicautogencost-estimationcrewaievalsevaluation-metricsgroqlangchainllmmistralollamaopenaiopenai-agents
Security Policy
Supported Versions
We currently support the following versions with security updates:
| Version | Supported |
|---|---|
| main | :white_check_mark: |
Reporting a Vulnerability
We take security vulnerabilities seriously. If you discover a security vulnerability in AgentOps, please report it responsibly.
How to Report
- Do NOT create a public GitHub issue for security vulnerabilities
- Email us directly at [email protected]
- Include the following information:
- Description of the vulnerability
- Steps to reproduce the issue
- Potential impact
- Suggested fix (if you have one)
What to Expect
- Acknowledgment: We'll acknowledge receipt of your report within 24 hours
- Investigation: We'll investigate and validate the vulnerability
- Timeline: We aim to provide an initial response within 72 hours
- Resolution: Critical vulnerabilities will be patched within 7 days
- Credit: We'll credit you in our security advisories (unless you prefer to remain anonymous)
Security Best Practices
When deploying AgentOps:
- Environment Variables: Never commit sensitive environment variables to version control
- HTTPS: Always use HTTPS in production
- Authentication: Use strong, unique passwords and enable 2FA where possible
- Updates: Keep dependencies and the platform updated
- Access Control: Follow the principle of least privilege
- Monitoring: Enable logging and monitoring for suspicious activity
Security Features
AgentOps includes several security features:
- JWT Authentication: Secure token-based authentication
- Role-based Access Control: Granular permissions system
- Input Validation: Comprehensive input sanitization
- Rate Limiting: Protection against abuse
- Audit Logging: Track all user actions
- Secure Headers: HTTPS enforcement and security headers
Vulnerability Disclosure Timeline
- Day 0: Vulnerability reported
- Day 1: Acknowledgment sent
- Days 1-3: Investigation and validation
- Days 3-7: Patch development and testing
- Day 7: Security release (for critical issues)
- Day 14: Public disclosure (after users have time to update)
Security Contacts
- Security Team: [email protected]
- General Contact: [email protected]
Thank you for helping keep AgentOps secure!