Nex vs ArcanAI

Nex-Bridge is the dedicated mobile management tool for your self-hosted local AI Agents. It bridges the gap between your mobile device and your desktop's local server, offering a seamless experience for developers and power users. IMPORTANT: This app is a connection tool only. It does not provide built-in AI models or generation services. You must have your own Local Gateway running on your computer to use this app. 【Core Features】 Secure Cloud Relay Access your local agents (like Clawdbot) from anywhere in the world. Our End-to-End Encrypted WebSocket relay service breaks through local network restrictions, allowing you to control your home server without complex VPN setups. AI Kanban Board More than just a chat interface. Nex-Bridge automatically parses task-related content from your agent's responses and organizes them into a visual Kanban board. Drag and drop tasks between "Todo", "Doing", and "Done" to keep your workflow moving. Native Performance Built with native iOS technologies, offering a smooth, responsive interface designed specifically for mobile task management. Privacy First (End-to-End Encryption) Zero-Knowledge Architecture. Your data is encrypted locally before transmission. The server only stores ciphertext, and your decryption keys/passwords are stored exclusively on your local device. We cannot access your data even if we wanted to. 【How to Use】 Set up and run the compatible Local Gateway on your desktop computer. Generate your connection Token. Enter the Token in Nex-Bridge to establish a secure, encrypted link. Start chatting and managing tasks remotely!

ArcanAI is a private, on-device AI chat app that runs open-source language models entirely on your iPhone or iPad. No accounts. No subscriptions. No cloud. No internet required. Import any GGUF model from Hugging Face and start chatting — every conversation happens locally, powered by hardware-accelerated inference using Apple's Metal framework. Your messages never leave your device. KEY FEATURES - Run AI models 100% offline — on a plane, off the grid, anywhere - Import any GGUF model from Hugging Face — choose the size and capability that fits your device - Store and switch between up to 5 models at once - Analyze documents — upload PDFs, spreadsheets, text files, CSVs, and more - GPU-accelerated inference for fast, streaming responses - Full conversation history with multiple independent chats - Edit messages and regenerate responses - Customize temperature, max tokens, and system prompts - Beautiful dark UI with markdown-rendered responses - Text-to-speech support SUPPORTED MODEL FAMILIES Llama, Gemma, Mistral, Phi, Qwen, and any ChatML-compatible model. RECOMMENDED STARTER MODELS - Llama 3.2 1B (~570 MB) — great for older devices - Gemma 2 2B (~1.0 GB) — balanced performance - Qwen 2.5 3B (~1.5 GB) — multilingual and code capabilities PRIVACY FIRST Zero data collection. Zero telemetry. Zero crash reporting. Zero cloud sync. Your conversations and model files stay on your device — always.