惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博客园_首页
IT之家
IT之家
博客园 - Franky
Stack Overflow Blog
Stack Overflow Blog
宝玉的分享
宝玉的分享
Recent Announcements
Recent Announcements
Engineering at Meta
Engineering at Meta
S
SegmentFault 最新的问题
V
Visual Studio Blog
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Last Week in AI
Last Week in AI
H
Help Net Security
V
V2EX
H
Hackread – Cybersecurity News, Data Breaches, AI and More
量子位
博客园 - 叶小钗
J
Java Code Geeks
博客园 - 【当耐特】
月光博客
月光博客
爱范儿
爱范儿
人人都是产品经理
人人都是产品经理
酷 壳 – CoolShell
酷 壳 – CoolShell
小众软件
小众软件

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店
GitHub - Heidar-An/Mira: Search for files semantically - ...
Heidaradar · 2026-05-29 · via Hacker News: Show HN

From Latin mīrāre - to look, to see, to behold.

Mira is a local-first desktop application that turns your folders into a searchable, intelligent workspace. Search files in plain English - no exact filenames required.


Install

Download the latest macOS build from the GitHub Releases page.

  1. Open the .dmg and drag Mira into Applications.

  2. Because Mira is not yet notarized by Apple, macOS will show "Mira is damaged and can't be opened" on first launch. Remove the quarantine flag by running this once in Terminal:

    xattr -cr /Applications/Mira.app
  3. Launch Mira from Applications.


Demo

mira_compressed.mp4

Features

  • 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

How it works

  1. Add a source - point Mira at any folder on your machine
  2. Index - Mira walks the directory tree, records file metadata, extracts text from supported formats, and generates semantic embeddings
  3. Search - queries are matched against metadata, extracted text, and semantic meaning simultaneously, then ranked by relevance

By 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.



Mira - look deeper into your files.



Building from source

Prerequisites: Rust, Bun, and the Tauri v2 system dependencies for your OS.

# Install dependencies
bun install

# Run in development (hot-reload)
bun run tauri dev

# Build for production
bun run tauri build

The distributable will be in src-tauri/target/release/bundle/.