Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

32 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CorteX

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.

Status

🚧 Work in progress

Quick Start

cp .env.example .env
uvicorn app.main:app --reload

Stack

  • 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)

About

Nexus is a FastAPI middleware that classifies prompts by task type and complexity, then routes them to the optimal LLM across Ollama and Groq using hot-reloadable YAML rules. Comes with Redis caching, API key auth, Postgres logging, and a full Prometheus + Grafana observability stack.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages