Whistant vs LLM Pigeon

Let Whistant do the Tedious Let Whistant do the tedious — your on-phone AI buddy that helps you get things done. Whistant doesn't just give ideas; it takes real actions, right from your iPhone. From Idea to Real Action Most AI tools stop at brainstorming or a single step. Whistant breaks your request into step-by-step subtasks and executes them: run Shortcuts, operate files, send messages or emails, place calls, browse the web, or call third-party APIs — all assembled like LEGO bricks and driven by a single prompt. Your Trusted On-Phone Colleague Whistant runs tools on your device and reasons about what to do next before acting. It thinks through multi-step actions for accuracy and reliability — then performs them with transparent, local execution. You stay in control: start, pause, or edit a running task and see exactly what's being executed in real time. Skills — Ready-Made Superpowers, Instantly Available Skills are self-contained capability packs that give Whistant new powers: connect Gmail, Google Calendar, Drive, Outlook, OneDrive, LinkedIn, and more with secure OAuth sign-in — no passwords stored. Install community skills from an ever-growing library of 600+ vetted recipes, or build and share your own. Each skill brings its own scripts, guides, and examples so the agent knows exactly how to act. JavaScript Terminal — Run Code, Your Way Whistant includes a full JavaScript runtime on your device. The agent can write and execute JS scripts to fetch APIs, transform data, automate logic, and chain operations — with access to Node-compatible modules and the ability to install packages on demand. Think of it as a programmable layer between your words and the world. Orchestrate iPhone Shortcuts — Build modular pieces for agent to use Apps Compose complex workflows by combining Shortcuts as modular pieces. Want to collect a file, summarize it, pick the best time on your calendar, and ping a contact with the result? Whistant stitches Shortcuts together safely and clearly so you don't have to script every detail. You can also build your own Shortcuts for Whistant to execute. Browse, Book, and Fill — From the Browser on Your Phone Whistant automates real browser interactions on your device — searching, filling booking forms, comparing options, and following checkout flows — while keeping the automation local. It can open links, capture page content, handle OAuth sign-in flows, and hand actions back to you for approval when needed. Your Model, Your Choice Connect Whistant to the AI backend that fits your needs. Use the built-in cloud service, point it at your own Ollama server, or register a custom backend. Choose different models for different job types — reasoning, execution, summarization — and switch vendors without losing your workflows. Privacy-First: Minimal Cloud Relay, Local-First Execution Most actions run on your device. When cloud LLM or API calls are needed, Whistant uses minimal, explicit relay for only those requests and only for features you enable. Permissions and prompts are clear — you always control which services Whistant may use. Save Time, Keep Control Work that used to take hours — gathering data, combining calendar + files + messages, or cross-app workflows — can be automated while you keep the final say. Whistant handles the details; you keep the control. Terms of Use: https://whisolla.com/terms.html#terms Privacy Policy: https://whisolla.com/terms.html#privacy

Put a full-featured AI assistant in your pocket—without sending a single word to any outside cloud. LLM Pigeon works together with LLM Pigeon Server on your Mac. • Type a message on your iPhone. • The text is stored inside your private iCloud files. • Your Mac picks it up, runs the large-language model locally, writes the reply, and CloudKit delivers the answer back to the phone. Why you’ll love it • 100 % privacy: messages never leave your own iCloud container; no analytics, no ads, no accounts. You can optionally add a search-engine API. • Real LLMs: choose from a set of built-in models or point the server at LM Studio or Ollama to swap in any model you prefer. How it works 1. Install LLM Pigeon Server (free) on a Mac that’s signed in with the same iCloud account. 2. Download the models you want and, if you’d like web search, enter a Serper API key. 3. Start a new chat in the iOS app. 4. Receive answers in seconds, even on hotel Wi-Fi. Zero data collection • No personal information • No usage analytics • No crash logs—everything stays on your devices • If you enable web search, only the queries your LLM generates are sent to Serper. Requirements • iPhone running iOS 17 or later • Mac running macOS 14 (Sonoma) or later with LLM Pigeon Server installed • iCloud Drive enabled on both devices