Chat with self-hosted large language models via Ollama API. Switch between models to test prompts. Support streaming and conversation context. Format responses with Markdown for tables, lists, and code. Specify server endpoint in settings.
Access and interact with private local AI models or open-source language models via OpenRouter API. Chat with customizable models, run smaller LLMs securely on-device, and connect to your own hosted models.
Use AI chat for instant responses without internet. Analyze files and PDFs securely. Generate images from text on device. Connect to desktop apps or cloud models for advanced tasks. Maintain privacy with encryption and no data tracking.
Allows real-time chat with AI models via server connection. Users can select models, search and manage conversations. Voice input and file/image uploads support RAG. Voice calling uses on-device processing.
Remote server access allows connection to self-hosted servers from any location. Per- system prompts let users customize conversation contexts. Prompt editing and regeneration enable refining interactions.
Access databases without server setup. Connect using TLS encryption and SSH tunnel. Authenticate with Secure Enclave Key or U2F/FIDO NFC Key. Create and alter tables. Explore, filter, sort, and search table data.
With AI models locally or via cloud APIs. Upload images or text files to improve conversations. Access multiple models including OpenWebUI, Ollama, and Gemini. Send and receive messages with real-time responses.