GitHub Repository

OpenAI-compatible LLM proxy in Go: cost-optimised routing, response caching, batch API, RAG pre-stage (pgvector + sentence-transformers), agent-gateway sub-service for CLI agents (Claude Code/Anthropic SDK/Gemini CLI)

2 starsGo

Kronaxis Router – Don't pay frontier prices when a local LLM is enough

Name: Kronaxis Router – Don't pay frontier prices when a local LLM is enough
Availability: InStock
Author: JasonDuke

by JasonDuke·Apr 7, 2026·2 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidBig BrainSolve My Problem

LLM cost routing with LoRA awareness when LiteLLM already handles basic proxying.

Strengths

•LoRA adapter routing knows which vLLM instances have which adapters loaded.
•50ms throughput batching dispatches bulk requests as single multi-prompt vLLM calls.
•Auto-routes to provider batch APIs for 50% cost reduction on bulk work.

Weaknesses

•LLM proxy space is crowded (LiteLLM, Helicone, Portkey) with no clear moat.
•Zero GitHub stars suggests very early stage with unproven production reliability.