Back to SeMo Lab

ThinkWell

A private AI companion that runs entirely on your device.

Features

A complete AI assistant that never leaves your device.

Fully Offline AI Chat

Real-time, token-by-token conversations powered by a language model running locally on your phone.

Private by Design

No cloud, no accounts, no analytics. Your conversations and settings never leave your device.

Rich, Readable Replies

Renders Markdown with LaTeX math, syntax-highlighted code, and tables — all bundled to work offline.

On-Demand Model Catalog

Pick from curated, phone-friendly models — Gemma, Llama, Qwen, DeepSeek, Phi, Mistral — with clear size and RAM tags.

Vision & Audio Input

Attach a photo or record speech and ask the model about it — multimodal, and still fully on-device.

Bring Your Own Model

Import any local GGUF model file and run it alongside the built-in catalog.

Export Anywhere

Save any reply as plain text, Markdown, Word, or PDF — with math, code, and tables preserved.

Guided Workflows

Structured templates for Decide, Plan, Debug, Brainstorm, Pros & Cons, and Explain.

Long-Term Memory & Backup

Optional on-device memory recalls facts across chats; export and restore everything as JSON.

30 Languages, Including RTL

A fully translated interface in 30 languages, with right-to-left support for Arabic, Farsi, and Hebrew.

Themes & Simple/Advanced Modes

Light or dark with five color palettes, plus Simple and Advanced modes for every kind of user.

Open Source (MIT)

Built with React Native and fully open source, so anyone can inspect exactly how it works.

Screenshots

See ThinkWell in action.

ThinkWell Screenshot 1
ThinkWell Screenshot 2
ThinkWell Screenshot 3
ThinkWell Screenshot 4
ThinkWell Screenshot 5