Back to directory

OvertChat

A self-hosted chat application for local and self-hosted language models, positioned as a simpler alternative to Open WebUI, with bundled speech and web-search services so it needs no cloud provider API keys to get started.

OvertChat

OvertChat is a self-hosted chat interface for everyday use with local or remote language models. It connects to inference servers such as vLLM, llama.cpp or SGLang that the user already runs, or to a hosted provider, and keeps conversation history on the user's own server rather than in a cloud account.

A guided installer sets up Docker, configuration and secrets, and can bundle SearXNG for web search, Kokoro for text-to-speech and Parakeet for speech-to-text, so a fully local setup needs no provider API keys or paid credits. The interface supports collapsible reasoning and tool-activity display, projects, reusable files, searchable history, light and dark themes, and multiple accounts so a household can share the same local models with separate conversations. A command-line tool manages the installation, its services and updates.

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.