* [yzma v1.15.0](https://github.com/hybridgroup/yzma) – Go-based library for hardware-accelerated local inference with llama.cpp integration.

* [Jan - Open-source ChatGPT replacement v0.8.2](https://github.com/janhq/jan) – Runs local and cloud AI models with privacy-focused control and customizable assistants.

* [llama-swap v219](https://github.com/mostlygeek/llama-swap) – Reliable on-demand model switching between local OpenAI-compatible inference servers without restarting applications.