HN Showcase
Back to browse
GitHub Repository
3 stars

GreyFox – Free self-hosted AI proxy, token quotas, and local cache

by SkilfulFox·Jun 21, 2026·3 points·0 comments
Visit ProjectView on HN

AI Analysis

●MidSolve My Problem

Yet another AI proxy when LiteLLM and Helicone already dominate.

Strengths
  • •SQLite storage means no external database dependencies to manage
  • •Mock mode enables zero-cost onboarding and demos without live keys
  • •Exact response cache reduces redundant token spend on repeated queries
Weaknesses
  • •5-user limit makes it unusable for most actual teams
  • •No differentiation from established players like LiteLLM or Portkey
Category
AI/ML
Target Audience

Teams managing LLM usage across multiple developers

Similar To

LiteLLM · Helicone · Portkey

Similar Projects

Developer Tools●●Solid

Docker-whisper: Self-hosted Whisper speech-to-text server (OpenAI API)

One-command Docker deploy from hwdsl2, who maintains trusted WireGuard and OpenVPN images.

CozySolve My Problem
hwdsl2
612mo ago
Developer Tools●●Solid

TokenMeter – Open-source observability layer for LLM token costs

Proxying every LLM call to log tokens is the right kind of blunt instrument — you get per-developer, per-model cost telemetry immediately. Smart routing and the built-in semantic cache (claims 45–80% savings) are the most useful ideas here, but the default SQLite backend and admin/admin creds scream MVP rather than production-ready scale.

Solve My ProblemNiche Gem
Mohit8880
134mo ago