Back to directory

Kronk

A Go SDK and model server for hardware-accelerated local inference, wrapping llama.cpp, whisper.cpp and stable-diffusion.cpp behind high-level Go APIs and OpenAI- and Anthropic-compatible endpoints.

Kronk

Kronk is a Go SDK and model server for local, hardware-accelerated inference that avoids requiring Python or a separate model-serving stack. Its Kronk component runs text, vision, embedding and reranking models through llama.cpp; a component called Bucky runs speech-to-text through whisper.cpp; and an experimental component called Malina, currently SDK-only, runs image generation through stable-diffusion.cpp.

The model server built on these SDKs exposes OpenAI-compatible Chat Completions, Responses, embeddings, reranking and audio-transcription APIs, plus an Anthropic-compatible Messages API, along with a browser interface for model management, security and observability, and integrations with OpenWebUI, OpenCode and Claude Code. It installs through Homebrew or go install, downloading compatible native libraries and model files automatically on first use, with a container path available for production deployment.

More in Inference

See all 770
  • OpenDecision

    deepanwadhwa.github.io

    An open-source Python package that answers typed questions about application state or documents using a local natural-language-inference model, returning structured choice, score, yes/no or evidence-relation values instead of free text.

  • Lifeboat

    iterate.ai

    A local inference server that puts an OpenAI- and Anthropic-compatible API in front of open-weight language models running on hardware you control, from a laptop to a GPU cluster.

  • Claude S40

    github.com

    An unofficial Claude chat client for 2007-era Nokia Series 40 phones, built as a Java ME app plus a small Go relay server, with web search, reading mode and saved chats.