{"slug": "show-hn-mira-search-for-files-semantically-no-exact-filenames-required", "title": "Show HN: Mira – Search for files semantically – no exact filenames required", "summary": "A developer released Mira, a local-first desktop application that enables users to search files using plain English without requiring exact filenames. The app indexes folders locally, extracting metadata and text from PDFs and documents while generating semantic embeddings for meaning-based retrieval, with an optional Gemini API provider for cloud processing. Mira is available for macOS via GitHub Releases, though users must remove a quarantine flag on first launch due to the app not being notarized by Apple.", "body_md": "From Latinmīrāre-to look, to see, to behold.\n\nMira is a local-first desktop application that turns your folders into a searchable, intelligent workspace. Search files in plain English - no exact filenames required.\n\nDownload the latest macOS build from the [GitHub Releases page](https://github.com/Heidar-An/Mira/releases/latest).\n\n-\nOpen the\n\n`.dmg`\n\nand drag**Mira** into`Applications`\n\n. -\nBecause Mira is not yet notarized by Apple, macOS will show\n\n*\"Mira is damaged and can't be opened\"*on first launch. Remove the quarantine flag by running this once in Terminal:\n\n```\nxattr -cr /Applications/Mira.app\n```\n\n-\nLaunch Mira from\n\n`Applications`\n\n.\n\n## mira_compressed.mp4\n\n**Metadata search**- instantly query file names, types, sizes, and dates across indexed folders** Content extraction**- full-text search inside PDFs, documents, and text files** Semantic search**- meaning-based retrieval powered by local embeddings by default, with an optional Gemini API provider** Live indexing**- add a source folder and Mira begins indexing in the background immediately** File preview**- open or reveal any result directly from the app\n\n**Add a source**- point Mira at any folder on your machine** Index**- Mira walks the directory tree, records file metadata, extracts text from supported formats, and generates semantic embeddings**Search**- queries are matched against metadata, extracted text, and semantic meaning simultaneously, then ranked by relevance\n\nBy default, processing happens locally and your files never leave your device. If you enable the optional Gemini API provider in settings, Mira sends the content needed for embeddings to Google's API using the key you provide.\n\n*Mira - look deeper into your files.*\n\n**Prerequisites:** Rust, Bun, and the [Tauri v2 system dependencies](https://tauri.app/start/prerequisites/) for your OS.\n\n```\n# Install dependencies\nbun install\n\n# Run in development (hot-reload)\nbun run tauri dev\n\n# Build for production\nbun run tauri build\n```\n\nThe distributable will be in `src-tauri/target/release/bundle/`\n\n.", "url": "https://wpnews.pro/news/show-hn-mira-search-for-files-semantically-no-exact-filenames-required", "canonical_source": "https://github.com/Heidar-An/Mira", "published_at": "2026-05-28 23:37:18+00:00", "updated_at": "2026-05-29 00:15:53.977388+00:00", "lang": "en", "topics": ["ai-tools", "ai-products", "ai-infrastructure"], "entities": ["Mira", "GitHub", "Apple", "Gemini", "Heidar-An"], "alternates": {"html": "https://wpnews.pro/news/show-hn-mira-search-for-files-semantically-no-exact-filenames-required", "markdown": "https://wpnews.pro/news/show-hn-mira-search-for-files-semantically-no-exact-filenames-required.md", "text": "https://wpnews.pro/news/show-hn-mira-search-for-files-semantically-no-exact-filenames-required.txt", "jsonld": "https://wpnews.pro/news/show-hn-mira-search-for-files-semantically-no-exact-filenames-required.jsonld"}}