# Inferoa

> Inference-native Tokenmaxxing Agent Harness for Loop Engineering

Run recursive long-horizon loops while tokenmaxxing prefix cache, context optimization, vLLM Semantic Router, vLLM serving, Omni, RTK, and CodeGraph.

## Facts
- Website: https://inferoa.agentic-in.ai
- Made by: agentic-in
- Category: AI agents & assistants
- Licence: Apache-2.0
- GitHub: https://github.com/agentic-in/inferoa (569 stars)
- Stage: Live

Listing page: https://launchwoo.com/p/inferoa
Listed on LaunchWoo, a directory of AI apps, developer tools and AI devices: https://launchwoo.com/launches