SamurAIGPT/neverdown
Automatic failover across generative AI providers. Never let your app go down when Fal or Replicate does.
Implements async polling with automatic provider cooldown (60s) to prevent hammering failed services, while exposing provider identity and latency metrics per request. Supports FLUX model variants across Fal and Replicate with configurable failover ordering, and raises granular exceptions (`AllProvidersFailedError`, `ProviderUnavailableError`, `JobTimeoutError`) to distinguish between transient outages and permanent failures.
Stars
9
Forks
4
Language
Python
License
—
Category
Last pushed
Mar 19, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/SamurAIGPT/neverdown"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Mateusz-Dera/ROCm-AI-Installer
Installation script for an AI applications using ROCm on Linux.
LlmKira/novelai-python
✨ NovelAI api python sdk, easy to use, modern and user-friendly.
caru-ini/novelai-sdk
✒NovelAI API SDK for Python with rich type hints and strong Pydantic v2 validation.
CodeBoy2006/falProxy
A high-performance, self-hosted Deno proxy that makes Fal.ai's powerful models (Flux, SDXL,...
intelligencedev/eternal
Eternal is an experimental platform for machine learning models and workflows.