Langfuse

GPU-optimized inference microservices for deploying AI models

Evaluation and observability for AI apps in production

Enterprise access to OpenAI models via Microsoft Azure

One API for Claude, Llama, Titan, and more on AWS

AI-first code editor, forked from VS Code

Fast, cheap inference for open-source models

Real-time code analysis and secure coding assistant

Self-hostable AI code completion for regulated industries

Cloud IDE where you can describe an app and Replit builds it