Introducing Pezzo – a developer-centric LLMOps platform designed to streamline Generative AI integrations. As Generative AI gains traction, we've observed a gap in tools catering to product teams and developers. Most are oriented toward ML/AI experts. That's why we created Pezzo - fully open-source under Apache 2.0.

GitHub: https://github.com/pezzolabs/pezzo

Why Pezzo?

- Centralized Prompt Management: Think email templates but for prompts. Design, test, and publish prompts without undergoing an extensive release cycle.

- Observability & Insights: Comprehensive dashboards that offer insights into cost metrics, AI provider expenses, success/error rates, and anomaly detection. Be in control of your AI operations.

- Efficient Request Caching: Out-of-the-box caching reduces costs and redundancy. Especially valuable during local development with repetitive LLM requests.

Future Roadmap: We're working on issue auto-suggestions, continuous prompt improvements, cost optimization, and security threat flagging, among other features.

If you'd like to try it out, we've made our Cloud version available: https://pezzo.ai. Note: It runs the identical code as our open-source version!

Additionally, we're always looking for contributors, so if you're interested - we'd love to hear from you.