Back to browse
GitHub Repository

Self-hosted AI reliability gateway - LLM failover, atomic budget caps, PII redaction. Drop-in OpenAI SDK compatible.

0 starsTypeScript

Selixes - Self-hosted LLM failover gateway, budget caps and PII

by selixes·Jun 28, 2026·3 points·0 comments

AI Analysis

●●SolidSolve My ProblemShip It

Sub-15ms failover and atomic budget caps, but LiteLLM and Portkey exist.

Strengths
  • Atomic Redis budget caps that survive crashes and prevent runaway agent spending
  • Pre-TTFT failover detection switches providers before user sees any error
  • Drop-in OpenAI SDK compatibility requires only two lines of code changes
Weaknesses
  • LLM gateway space is crowded with LiteLLM, Portkey, Helicone already solving this
  • Zero stars and forks suggests very early stage with unproven reliability
Target Audience

Backend developers and AI engineers building production LLM applications

Similar To

LiteLLM · Portkey · Helicone

Post Description

We built Selixes, a self-hosted LLM failover gateway with atomic budget caps and PII redaction. Repo: https://github.com/selixes/gateway

Similar Projects

AI/ML●●Solid

Routiium – self-hosted LLM gateway with a tool-result guard

Guards tool outputs against injection attacks, unlike LiteLLM or Helicone.

Solve My ProblemBig Brain
deadpixel
202mo ago