OpenHarbor vs Astola

**OpenHarbor Manager Assistant** is a lightweight management client built for the Lobster Gateway, allowing you to connect to and manage your local or LAN-based AI Agent Gateway anytime, anywhere from your phone. ## Main Features ### WebSocket Gateway Connection Supports both `ws://` and `wss://` protocols. Optional Gateway Token support, compatible with Gateway device authentication (Ed25519) and automatic pairing flow. ### Multiple Lobster Configurations Save and manage multiple Gateway profiles (Lobster 1, Lobster 2, etc.). Quickly switch between them from the top bar, with independent connection status and chat history for each profile. ### Gateway Sessions Connect to the Gateway in operator mode and chat with your AI Agent in real time. Conversation history is shared with the browser Control UI session (`agent:main:main`). ### Status Monitoring Monitor Gateway health, running status, and online devices/channels in real time. ### Model Configuration View and switch AI models (supports popular providers like DeepSeek). Update API Keys with one tap and apply changes instantly without restarting the Gateway. ### Skill Search Search or browse trending Skills through the ClawHub API. Copy installation commands with one tap and run them on the computer hosting the Gateway to install Skills instantly. ## Use Cases * Remotely monitor your local or LAN-based AI Agent from your phone * Switch AI models or update API Keys without opening your computer * Quickly search and install Skills from ClawHub ## Notes This app is a management tool for the Lobster Gateway and does not provide standalone generative AI services. Before using the app, you need to deploy and run your own Lobster Gateway (recommended version: v2026.2.26 or later).

Your human friends. Your AI friends. One conversation, built for all of you. Astola turns the AI tool you already use into a friend with a name, a face and a voice — in the same chat as the people you know. Claude, ChatGPT, or a model running on your own Mac. Work together. Laugh together. Grow together. Astola comes in two halves: the app on your iPhone, and Astola Host on a Mac you own. Your AI friends live on that Mac — that is where they think, and where they get work done. What you can do: • Give an AI friend a portrait, a name, a voice and a personality, then chat with them like anyone else • Put people and AI friends in the same group chat, and @mention whoever should answer • Send text, photos, files and voice messages — or hold to talk and hear the reply out loud • Give an AI friend a folder on your Mac and a job to do; it works there and messages you the result • Choose the brain behind each AI friend: your own Claude or ChatGPT account, a compatible endpoint, or a local model that runs on your Mac with no account and no per-message cost • Add real friends by scanning a QR code, and share a conversation with them • Your AI friends remember earlier conversations, so you can pick up where you left off You stay in control. Chats are saved on your devices and synced through your own iCloud. You choose which AI service each friend uses. Astola has no account system and does not operate a central chat server. Getting started: 1) Install Astola on your iPhone and set up your profile 2) Install Astola Host on a Mac using the same iCloud account 3) Create an AI friend, choose its brain, and start chatting Shared conversations are available to their participants. Cloud AI and media providers process the context sent to them under their own policies. Compatible local inference is a separate configuration choice and does not disable iCloud sync or external tools. Requires iOS or iPadOS 18 or later. AI friends need an online Apple Silicon Mac running macOS 15 or later, Astola Host and a configured, supported agent runtime. Your own devices use the same iCloud account. Provider subscriptions or API charges may apply. An active iCloud account with available storage is required for syncing and shared conversations.