Open Source TypeScript Search Software

MiniSearch is a minimalist web search application with a built-in AI assistant that runs largely inside the browser for privacy-focused information retrieval. The project combines metasearch capabilities with local or remote language model inference to provide conversational answers alongside traditional search results. It is designed to be lightweight, easy to deploy with Docker, and configurable for both personal and hosted use cases. The platform supports browser-level integration so users can set it as their default search engine for quick access. Its architecture emphasizes privacy by avoiding tracking and minimizing data collection while still enabling advanced AI features. Overall, MiniSearch targets users who want a self-hosted, Perplexity-style search experience with strong control over data and models.

Syncdrome is a standalone tool that creates a comprehensive catalog of files from your personal hard drives. It enables rapid keyword searches, delivering results in a style similar to web search engines. When a drive is connected, you can directly open files with your system’s default applications. The application lets you designate a working folder for storing the file catalog, which can even be located on a cloud storage service like Dropbox or Google Drive for easy access from any device. With an intuitive interface, Syncdrome also provides a Navigator for exploring your synchronized drives, a Bookmark system to save your favorite files with comments, and a Folder Sync feature to keep directories consistent between locations. Additionally, its File Name Cleaner allows you to apply custom patterns and substitution rules to modify file names efficiently.

Web Page Application: https://shemeshg.github.io/desktop-search/ Github: https://github.com/shemeshg/desktop-search-code * Dropbox sync is performed manually (from admin screen) and not on interval.

Paul Graham GPT is a specialized AI-powered search and chat app built on a corpus of essays from Paul Graham, giving users the ability to query and discuss his writings in a conversational way. The repo stores the full text of his essays (chunked), uses embeddings (e.g. via OpenAI embeddings) to allow semantic search over that corpus, and hosts a chat interface that combines retrieval results with LLM-based answering — enabling RAG (retrieval-augmented generation) over a fixed dataset. The app uses a Postgres database (with pgvector) hosted on Supabase for its embedding store, making the backend relatively simple and accessible, and the frontend is again built with Next.js/TypeScript for a modern responsive UI. By pulling together search and chat, it creates a useful tool both for readers who want to revisit or explore Paul Graham’s ideas thematically, and for learners or researchers who want to query specific essays or concepts quickly.

The name “SWR” is derived from stale-while-revalidate, a HTTP cache invalidation strategy popularized by HTTP RFC 5861. SWR is a strategy to first return the data from cache (stale), then send the fetch request (revalidate), and finally come with the up-to-date data. With SWR, components will get a stream of data updates constantly and automatically. And the UI will be always fast and reactive. With just one single line of code, you can simplify the logic of data fetching in your project, and also have all many amazing features out-of-the-box. SWR has you covered in all aspects of speed, correctness, and stability to help you build better experiences. Fast page navigation, polling on interval, data dependency, revalidation on focus, revalidation on network recovery, local mutation (Optimistic UI), smart error retry, pagination and scroll position recovery, React Suspense, and more.