rag vs Nekoni

RAG Bot — Private AI on Your Device Have natural conversations with locally-running large language models. Your chats stay on your device with full conversation history and search. Your Documents, AI-Powered Upload PDFs or DOCX files. RAG Bot generates embeddings so you can chat with your documents using retrieval-augmented generation. Visualize your document embeddings in an interactive 3D atlas. Choose Your Model Browse and download from three AI providers (Cactus, ExecuTorch, llama.rn). Filter by type (LLM or embedding), size, capabilities like vision and tool calling — find the right model for your hardware. Built for Performance Real-time device monitoring shows memory and storage usage so you always know what your device can handle. Optimized for Apple Silicon with multiple inference backends. Key Features 100% offline — no internet required after model download Multiple model providers and quantization options Document RAG with PDF, DOCX support Conversation history with full search Vision and tool-calling capable models Real-time device resource monitoring 3D embedding visualization

Nekoni connects your iPhone to an AI agent running on your own hardware - no cloud, no subscription, no data leaving your home. Most AI assistants send everything you type to a third-party server. Nekoni is different. You run the AI yourself, on your own machine, and your phone connects directly to it over an encrypted P2P channel. HOW IT WORKS Install the agent on any computer at home, scan a QR code to pair your phone, and start chatting. The connection goes device-to-device - your messages never touch an external server. FEATURES Chat - Talk to any model you run locally via Ollama: Llama, Mistral, Gemma, and more. Full conversation history with the ability to continue past sessions. Knowledge Base - Upload documents (PDF, text, markdown) and ask questions about them. The agent retrieves relevant context automatically before answering. Skills - Create named prompt templates for tasks you repeat often. Run them on demand or schedule them to run automatically on a schedule. Privacy by Design - Your identity is an Ed25519 key pair generated on your device and never shared. Pairing requires explicit approval from your dashboard. Every message is signed and authenticated. Works Anywhere - The connection uses WebRTC, the same technology behind video calls. Once paired, you can reach your home agent from anywhere in the world. REQUIREMENTS Nekoni requires the agent software running on a computer you control. Setup instructions and the open-source agent are available at https://github.com/nekonihq/nekoni.