Provider-agnostic LLM routing middleware — classify, route, observe.
CorteX sits between your application and multiple LLM providers, automatically classifying each prompt and routing it to the most suitable model based on task type and complexity.
🚧 Work in progress
cp .env.example .env
uvicorn app.main:app --reload- FastAPI — async REST API
- PostgreSQL — request audit log
- Redis — caching and rate limiting
- Prometheus + Grafana — metrics and dashboards
- Ollama — local LLM inference
- Groq — cloud LLM inference (free tier)