- Category
- Developer Tools
- Rank
- No. 3433Tools index
- Pricing
- Open Source
- Type
- TOOL
- Use case
- Models: Train & Run
- Interfaces
- API
- GitHub
- 45 stars
- Latest release
- v0.1.8
- Date
About
Goethe turns a Linux machine with NVIDIA GPUs into a self-hosted model API compatible with OpenAI, Anthropic and LiteLLM clients. You install it, load a model, and issue API keys that can be rate-limited, scoped, expired or revoked. It can serve several models at once, split large models across GPUs, and restore loaded models after a reboot or crash. Prompts and data stay on hardware you control.
Tags
inferenceself-hostedllmnvidiaopenai-compatibleapi
Tech Stack
Docker
Comments (0)
No comments yet
Editorially curated, with community endorsements as a secondary signal. Corrections welcome.