Phantasm vs Joey MCP Client Lite

Phantasm is a private AI chat client for the backend you already run. Point it at your own server: Ollama, vLLM, llama.cpp, or any OpenAI-compatible endpoint and chat with your own models over your own network. No account, no middleman, no data collection. YOUR SERVER, YOUR RULES • Connect with just a URL and a token — works against a bare Ollama out of the box • Add the open-source Phantasm orchestrator to unlock web search, image generation, and research modes • Multiple backend profiles for home network, VPN, or tunnel setups • Your token lives in the iOS Keychain; conversations are stored only on your phone A REAL CHAT EXPERIENCE • Fast streaming responses with markdown, syntax-highlighted code blocks with copy, and charts • Attach photos and files — vision models can see your images • Generated images appear inline; save or share them • Dictate messages with on-device transcription and have replies read aloud • Long generations survive backgrounding and pick up where they left off • Ask Phantasm from Siri and Shortcuts TOOLS ON YOUR TERMS • Per-chat toggles for web access and image generation • Optional device tools — location, calendar, Apple Health — are off by default and only shared with your own backend when you enable them • See the model's reasoning when a thinking model is selected PRIVATE BY DESIGN Phantasm operates no servers and collects no data. The app talks exclusively to the backend you configure — nothing else. What you say to your AI is between you and your hardware. Phantasm requires an OpenAI-compatible server that you provide (for example, Ollama running on your own machine). Feature availability depends on your backend's capabilities.

Joey MCP Client Lite is an open-source AI chat app that lets you connect to any AI model and extend it with powerful tools and services — both remote and right on your device. Chat with any AI model Bring your own AI in whichever way suits you: ▶ OpenRouter — access hundreds of leading models including GPT, Claude, Gemini, Deepseek and more. Connect via OAuth with configurable spending limits, so you stay in control — no surprise bills. ▶ Any OpenAI-compatible endpoint — point Joey at your own base URL and API key to use OpenAI directly, a self-hosted model, Ollama, or any compatible provider. Connect your tools and services Joey supports the Model Context Protocol (MCP), an open standard that lets AI models interact with external tools and services. Connect to remote MCP servers over HTTP, giving your conversations access to services like Google Drive, Slack, email, calendars, CRMs, and more. On-device tools Give the AI safe, built-in access to your device — no server required. Ask it to check the time anywhere, get your location, look up contacts, draft a message or email, start a call, or search and create calendar events and reminders. Actions that leave the app (like sending a message or placing a call) always require a tap from you. Image support Send images to vision-capable models directly from your camera, gallery, or clipboard. Great for asking questions about screenshots, documents, and photos. Advanced MCP features Joey goes beyond basic tool calling: ▶ Sampling — MCP servers can request additional LLM completions, enabling complex multi-step AI workflows ▶ Elicitation — MCP servers can present interactive forms to gather input from you mid-conversation Lite vs Premium Joey MCP Client Lite includes core functionality, with an optional one-time in-app purchase to unlock everything. Included in Lite: ▶ Chat with any model via OpenRouter or your own OpenAI-compatible endpoint ▶ One active conversation ▶ One MCP server ▶ Image support, sampling, and elicitation Joey Premium (one-time purchase — yours forever) unlocks: ▶ Unlimited conversation history — keep every chat instead of just the current one ▶ Unlimited MCP servers — connect as many as you like ▶ On-device tools — time, location, contacts, messaging, calls, email, calendar, and reminders Open source Joey is fully open source. Everything is unlocked when you build it yourself. Browse the code, report issues, or contribute on GitHub: https://github.com/benkaiser/joey-mcp-client-flutter