Pezzo
An open-source, cloud-native LLMOps platform for designing and versioning prompts, observing and troubleshooting AI operations, and delivering prompt changes instantly across an application.
Pezzo is a fully cloud-native, open-source LLMOps platform for observing and monitoring AI operations, managing and versioning prompts in one place, and delivering AI changes without a redeploy. It aims to help teams collaborate on prompts, troubleshoot issues, and reduce cost and latency.
It provides Node.js, Python and LangChain client libraries with consistent support for prompt management, observability and caching across all three. The stack runs on open-source infrastructure, PostgreSQL, ClickHouse, Redis and Supertokens, deployable through Docker Compose, with a GraphQL API and a web console for managing prompts and inspecting telemetry.
It is written in TypeScript and released under the Apache 2.0 license.