Sleeveworks vs Local Inference OnDevice Agent

Sleeveworks is private AI with a point of view. Choose a personality, type or talk, and keep the conversation close. Its language model runs directly on your iPhone instead of sending every thought to a cloud AI service. MEET THE CAST Start with Companion, Gremlin, Pengo, Shekky, and Sage. Browse every character, read sample replies, and hear their on-device voice before choosing. Expand your cast with one-time personality unlocks, including Atlas the accountability coach, Bea the warm Southern grandmother, Quill the theatrical bard, Specter the gothic storyteller, and more. Each personality brings a distinct voice, attitude, and way of seeing the conversation. VOICE THAT FEELS LIKE CONVERSATION Tap Talk, speak naturally, and hear Sleeveworks answer. After a reply, the microphone can reopen automatically so the conversation keeps moving. When parallel capture is available, Sleeveworks can continue listening while it responds and place longer interjections in Up Next instead of derailing the current answer. Interrupt at any time when you want to take the floor. PRIVATE BY DESIGN After the one-time model download, core conversations are processed on your iPhone and can work without an internet connection. No account. No advertising. No tracking or analytics. No API key. Optional Wikipedia lookup is off by default and only connects when you enable it. MADE FOR REAL CONVERSATIONS - Keep local conversation history and context - Choose an on-device model suited to your iPhone - Switch personalities without changing apps - Preview character voices before choosing - Type while a response is still being generated - Stop a response without clearing the conversation - Choose between Paperwhite and system themes - Continue chatting after the model is downloaded, even offline Sleeveworks puts the model, the conversation, and the cast directly on your iPhone. Some personalities require a one-time in-app purchase. Initial setup requires an internet connection and sufficient storage to download an on-device language model. Model availability and performance vary by device.

Your AI. Your phone. Nobody else's business. LocalInference runs powerful open AI models entirely on your device. Your conversations never leave your phone — no account, no cloud, no analytics, no tracking. Ever. PRIVATE BY ARCHITECTURE, NOT BY PROMISE • Everything runs on-device; works fully offline after a one-time model download • Zero data collection — we couldn't read your chats if we wanted to • API keys (optional) stored in the secure keychain, sent only to the provider you chose A REAL ASSISTANT, NOT JUST A CHATBOT • Tools: calculator, web search, date & time, webpage reading • Contacts & calendar integration — every write action asks you first • Ask about photos with vision models • Reads answers aloud with on-device voices BUILT FOR TINKERERS • 16 curated models from 0.5B to 8B — Qwen3, Llama, Gemma, DeepSeek R1, Phi, SmolVLM • Only models that fit your device's memory are offered • Live tok/s, time-to-first-token, and token counts per response • Thinking models show their reasoning in collapsible blocks • Bring your own keys: Anthropic, OpenAI, Google — or any OpenAI-compatible server (llama.cpp, LM Studio, Ollama) on your own network Built with Llama. Gemma models provided under the Gemma Terms of Use.