Pumli vs Whistant

A world of your own. Meet Pumli, your private AI companion for everyday questions, thoughtful research and a little imagination. Start with a model on your phone. Add useful connections when you choose. Make the assistant feel like yours. BIG AI, RIGHT HERE Download a compatible model and chat on your device, even offline. Explore MiniCPM-V 4.7 35B-A3B on compatible hardware: 35 billion total parameters, with about 3 billion active per token. Prefer something smaller? Choose a compact model that fits your phone, storage and task. A WORLD OF LOCAL MODELS Discover compatible GGUF models through Hugging Face search, alongside curated choices with Hugging Face and ModelScope download sources. Manage downloads, see the models already on your device and remove those you no longer need. Model compatibility and performance vary; not every model file can run on every device. YOUR PRIVATE LITTLE SPACE Local inference runs on your device. Keep conversation history close, start a fresh chat, and review or delete what you save. Give your assistant a name, adjust its instructions, and view, edit or remove its locally saved memories. Local conversations do not require a general Pumli cloud chat account. CONNECT BY CHOICE Bring notes, code, documentation and search into the conversation with supported connections such as Notion, GitHub, Context7, Microsoft Learn and remote MCP servers. Search the web through the services you enable. Connectors are optional: choose access, review requests and control your tool-approval settings. A HELPING HAND ON IPHONE Use supported phone actions for calls, Messages, Contacts, Calendar, Reminders, Maps, Health and Fitness. These features require the relevant permissions and your choice to enable them. Health and Fitness tools are read-only and designed to show results on your device. Phone and messaging actions use the appropriate system interface. FOLLOW YOUR CURIOSITY Research mode explores bigger questions across multiple steps using enabled tools. Choose a depth, follow the progress and open the sources behind the answer. Use it to compare ideas, investigate a topic or bring scattered information together. AI research still needs your judgement: check important facts and source material. FIND THE WORDS Ask for an email draft, then review and edit the recipient, subject and message. Open the draft in Mail, choose your sending account and send when you are ready. Pumli 3.0 uses this Mail handoff; direct Gmail and Outlook account connectors are not part of this release. MAKE SOMETHING NEW Create images with optional online providers, including Gemini, or turn a prompt and supported reference media into a Seedance video. Preview and save supported creations to your device. Use your own eligible provider account or API key; availability, safety rules, quotas and provider fees apply. SPEAK YOUR WAY Use local dictation after downloading a compatible speech model, or choose optional online realtime voice. Move between writing, speaking, researching and creating in one personal space. KNOW WHAT STAYS LOCAL Online AI, connected search, remote tools, realtime voice and cloud generation require internet access and send the information needed for the task to your chosen provider. Some services require separate accounts, keys or usage fees. Pumli does not promise that online providers retain no data. Large models need substantial storage and compatible hardware. Speed, context and available features vary by device and region. AI can make mistakes; review important answers and external actions before relying on them. Pumli is an independent app. Model and service names belong to their respective owners.

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