TypingMind

TypingMind is a browser chat frontend for people who want to choose their model providers and manage conversations in one place. It connects to cloud APIs such as OpenAI, Claude and Gemini, and supports custom endpoints for locally hosted models such as Ollama and LocalAI. The frontend does not run model inference itself.

Its static self-host package can run on a local device or private server, or be served from static web hosting. Conversations, settings and API keys are stored locally by default. Choosing a local model endpoint keeps inference with that server; cloud providers receive the requests you send to them.

The interface includes searchable conversations, folders, reusable prompts, conversation branching and import/export. Document uploads, web search, plugins and speech features extend chat according to the connected services.

Static self-hosting has limits: the app needs HTTPS outside localhost, must be deployed at the domain root, and its branding cannot be customized. That package can lag behind the hosted app. The separate Team edition has different deployment and administration capabilities.