Back to directory

DKST LLM Chat Server

A local web chat interface that connects LM Studio and other OpenAI-compatible model providers to an in-app tool runtime and the Supertonic text-to-speech engine, with hybrid memory search across conversations.

DKST LLM Chat Server

DKST LLM Chat Server is a local LLM web interface that combines several model providers, such as LM Studio and OpenAI-compatible APIs, with an in-app tool runtime and Supertonic text-to-speech for a personal-assistant style experience.

It keeps a user profile and long-term memory of the conversation, retrieved through a hybrid FTS5-plus-vector search, and scores stored memories so less useful ones are forgotten over time. Provider-independent tools such as web search, memory and system tools run inside the app without registering each one separately per provider, and it supports multimodal image upload for vision models.

It is built with Go and a Wails desktop shell, requires Node.js to build, and serves a chat UI on port 8080 and an HTTP API on port 8081; a SQLite database holds the memory store.

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.