hikyaku

hikyaku

wentbackward

A superfast proxy and smart load-balancer for AI Inference — virtualize models, share local and provider back-ends, optimal caching, lock-in sampling parameters, debug message flow and obtain OTel metrics

load-balancer
View on GitHub Website
9 Stars
5 Forks
0 Watchers
Go Language
mit License
73.6 SrcLog Score
Cost to Build
$668.0K
Market Value
$992.0K
How is this calculated?

Growth over time

2 data points  ·  2026-07-26 → 2026-08-10
Stars Forks Watchers
💬

How do you feel about this project?

Ask AI about hikyaku

Question copied to clipboard

What is the wentbackward/hikyaku GitHub project? Description: "A superfast proxy and smart load-balancer for AI Inference — virtualize models, share local and provider back-ends, optimal caching, lock-in sampling parameters, debug message flow and obtain OTel metrics". Written in Go. Explain what it does, its main use cases, key features, and who would benefit from using it.

Question is copied to clipboard — paste it after the AI opens.

How to clone hikyaku

Clone via HTTPS

git clone https://github.com/wentbackward/hikyaku.git

Clone via SSH

[email protected]:wentbackward/hikyaku.git

Download ZIP

Download main.zip

Found an issue?

Report bugs or request features on the hikyaku issue tracker:

Open GitHub Issues

Similar to hikyaku

pm2 traefik fabio armor nuster dpvs gobetween metallb roadrunner lura linkerd-tcp marathon-lb httpteleport multitor golb tempesta nixy dubbo3 styx awesome-nginx-security polaris-gslb slb portal sensu-plugins-aws KaHIP node-loadbalance Cekirdekler ansible-role-varnish docker-django-nginx-uwsgi-postgres-load-balance-tutorial tns