OneLLM: Offline AI & LLM Chat

Choose where your AI runs. OneLLM brings local language models, cloud providers and your own servers into one focused workspace. LOCAL AI Download a compatible GGUF model and chat on your device. After downloading, local inference works offline. CLOUD & YOUR SERVERS Bring your own API keys for supported providers, including OpenAI, Claude, Gemini, DeepSeek and Qwen. Connect to Ollama or your OpenClaw workspace. EVERYDAY TOOLS Write, edit, code and plan. Collect notes, recognize text from images with on-device OCR, and transcribe speech locally after downloading a compatible speech model. MADE FOR YOUR SPACE A refreshed interface, clear navigation, light and dark appearances, and layouts that adapt to your available screen space. BEFORE YOU START Local models need storage and memory; compatibility and speed depend on your device. Cloud features require internet access, your own API key and any provider charges. API access and subscriptions are not included. Ollama and OpenClaw require reachable servers configured by you. Local inference stays on your device. Online requests go to your selected provider or server. AI can make mistakes; check important results.