AgentOps-AI / AgentOps-AI/agentops

[Feature Request]: Add CometAPI support to AgentOps

Open
#1,258 0 comments 0 reactions 0 assignees View on GitHub
enhancement
Dominant language
Python
Stars
5.8k
Forks
619
PR merge metrics
No merged PRs in 30d

Description

### 💡 Feature Description and Proposed Solution

Add CometAPI as a supported LLM provider in AgentOps for comprehensive agent monitoring and observability. This integration would allow AgentOps to automatically track and monitor AI agents that use CometAPI models, providing cost tracking, performance analytics, and session replays for CometAPI-powered agents.

The integration would include:
- Automatic CometAPI LLM call tracking and cost monitoring
- Support for CometAPI models in AgentOps session replays
- Integration with existing AgentOps decorators (@agent, @operation, @session)

**CometAPI Resources**
- [CometAPI Website](https://www.cometapi.com/?utm_source=AgentOps&utm_campaign=integration&utm_medium=integration&utm_content=integration)
- [Docs](https://api.cometapi.com/doc)
- [Base URL](https://api.cometapi.com/v1/)
- [Models](https://api.cometapi.com/v1/models)
- [API Key](https://api.cometapi.com/console/token)
- [Pricing](https://api.cometapi.com/pricing)

**Implementation Offer**
We can implement this integration and submit a PR according to your project's standards and guidelines if you'd like.

### 🤔 Related Problem

AgentOps currently supports many LLM providers for agent monitoring, but lacks CometAPI integration. This limits users who want to leverage CometAPI's capabilities while maintaining comprehensive observability through AgentOps. Users need a unified monitoring solution that works across different LLM providers, including CometAPI.

### 🤝 Contribution

- [x] Yes, I'd be happy to submit a pull request with these changes.
- [x] I need some guidance on how to contribute.
- [ ] I'd prefer the AgentOps team to handle this update.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.