Submit a resource

Navigation

Back to directory

ConfiChat

A lightweight, multi-platform chat interface for local and cloud LLMs that can run fully offline and optionally encrypts stored chat history and files.

Visit website (opens in a new tab)codersfollies.com
ConfiChat

ConfiChat is a standalone chat interface for large language models that works with offline providers such as Ollama and LlamaCpp, running entirely on the local machine or network, as well as online providers such as OpenAI, Anthropic and Gemini through their APIs.

Chat sessions are stored locally as individual JSON files, with optional encryption of both chat history and any attached assets. Unlike solutions built around Docker and a suite of supporting tools, it is a single standalone application, aimed at users who want a streamlined interface without maintaining separate infrastructure.

Pre-built binaries are provided for several platforms; macOS and iOS builds are not distributed as binaries due to platform restrictions and must be compiled from source. It is written in Dart and licensed under Apache-2.0.

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.

Cookies

We use necessary cookies to run the site. Measurement and marketing are optional; neither is used today. Privacy policy