Lapis
Secure, offline AI chat assistant on your device
57 followers
Secure, offline AI chat assistant on your device
57 followers
Lapis brings a unique twist by running powerful open-source LLMs locally on your device, giving you a fully offline, private AI chat experience. Unlike cloud-based assistants, Lapis never sends your data to servers or collects it. You can load any Hugging Face model (like Gemma, Phi, LLaMA, GPT-OSS…) by pasting its URL. Manage your model library, optimize performance, and chat securely all free, no subscription needed
Products used by Lapis
Explore the tech stack and tools that power Lapis. See what products Lapis uses for development, design, marketing, analytics, and more.
LLMs 1
LLMs 1
Qwen3Think Deeper or Act Faster
5.0 (8 reviews)
I chose the Qwen model as the default starting in version 1.2 because it delivers an ideal balance of speed, accuracy, and lightweight performance. It runs efficiently on-device, uses very little storage, and responds quickly even on less powerful hardware. This makes it a perfect fit for an offline AI assistant where reliability, low resource usage, and a smooth user experience are essential.
Engineering & Development 2
Engineering & Development 2
GitHubHow people build software
5.0 (509 reviews)
I chose GitHub because it provides a reliable, transparent, and developer-friendly ecosystem for managing the project. Using Git allows me to track changes cleanly and collaborate efficiently, while GitHub Actions automates builds, tests, and deployments so updates are consistent and error-free. The Releases section makes it easy to share versioned builds and changelogs with users, ensuring everyone always has access to stable, well-documented updates.
Next.jsCreate web applications with the power of React components
5.0 (430 reviews)
chose Next.js because it offers a fast, reliable, and flexible framework for building modern web experiences. Its built-in routing, server-side rendering, and strong performance optimizations make it easy to deliver a smooth, SEO-friendly site while keeping the codebase clean and maintainable.