Use your locally running AI models to assist you in your web browsing.




The best open source alternative to GPT4ALL is Jan.ai. If that doesn't suit you, our users have ranked more than 100 alternatives to GPT4ALL and loads of them are open source so hopefully you can find a suitable replacement. Other interesting open source alternatives to GPT4ALL are Ensu, AnythingLLM, Alpaca - Ollama Client and Secret Llama.
Use your locally running AI models to assist you in your web browsing.




Local AI agents on your Mac. Private, offline, free. Open models run on Apple Silicon; add ChatGPT, Claude or Gemini only when you choose.



BionicGPT is an on-premise replacement for ChatGPT, offering dataset querying through RAG and data confidentiality



ChatGPT Infinity is a free (yet powerful) add-on that makes ChatGPT generate infinite answers on any topic!




Conduit is a mobile client for self-hosted Open WebUI servers. It supports streaming chat, the standard authentication methods, and home-screen integrations on both platforms.



5ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base and tools via model context protocol servers .




SmolChat allows you to download and run popular LLMs on your Android device, locally, without needing an internet connection. Customize the model used for each chat, tune settings like temperature and min-p, and pin your favourite chats on the home-screen with shortcuts.



Chat with generative language models locally on your computer with zero setup. LocalChat is a simple, easy to set up local AI chat built on top of llama.cpp. It requires no technical knowledge and enables users to experience ChatGPT-like behavior on their own machines — fully...

Empowering your conversations with real-time AI insights. CueFlow transcribes locally, analyzes dialogue, understands context, and provides timely assistance, helping you navigate various scenarios with confidence. And no any data privacy concerns.

Run LLMs on AMD Ryzen™ AI NPUs in minutes. Just like Ollama - but purpose-built and deeply optimized for the AMD NPUs.
You need Ollama running on your localhost with some model. Once Ollama is running the model can be pulled from Follamac or from command line. From command line type something like: Ollama pull llama3 If you wish to pull from Follamac you can write llama3 into "Model name to...

AI00 RWKV Server is an inference API server for the RWKV language model based upon the web-rwkv inference engine.