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

有赞技术团队
有赞技术团队
M
MIT News - Artificial intelligence
Hugging Face - Blog
Hugging Face - Blog
博客园 - 聂微东
量子位
S
SegmentFault 最新的问题
V
Visual Studio Blog
博客园 - 【当耐特】
Apple Machine Learning Research
Apple Machine Learning Research
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
小众软件
小众软件
Stack Overflow Blog
Stack Overflow Blog
Vercel News
Vercel News
D
Docker
J
Java Code Geeks
博客园 - 三生石上(FineUI控件)
博客园 - Franky
Recent Announcements
Recent Announcements
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
MongoDB | Blog
MongoDB | Blog
D
DataBreaches.Net
Y
Y Combinator Blog
云风的 BLOG
云风的 BLOG
V
V2EX

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 - iamnotagentleman/bad-photos-out: Definitely not ...
velieroglu · 2026-05-08 · via Hacker News: Show HN

BadPhotosOut icon

BadPhotosOut

A native macOS app that walks your Apple Photos library, asks a local Ollama vision model to judge each photo against a free-text criterion you supply, and surfaces the flagged photos with the model's reason. No automatic deletion — you review the list and delete in Photos manually.

Nothing leaves the Mac: photos are read via PhotoKit and sent only to a local Ollama server.

⚠️ Disclaimer: this app is vibe-coded. No warranty, no support, no guarantees about correctness, performance, or your photo library. Use at your own risk — you are solely responsible for any photos you choose to delete based on what this app shows you.

Setup

1. Install Ollama and pull a vision model

brew install ollama
ollama serve   # in one terminal, leave running
ollama pull llava   # in another terminal; or any other vision model

2. Generate the Xcode project

brew install xcodegen   # if not already installed
xcodegen generate

This produces BadPhotosOut.xcodeproj.

3. Build and run

Either open the project in Xcode and hit Run, or from the command line:

xcodebuild -project BadPhotosOut.xcodeproj -scheme BadPhotosOut -configuration Debug build
open build/Debug/BadPhotosOut.app   # path may differ depending on derived data location

On first run macOS will ask for Photos access. Grant it.

4. Use it

  1. In the sidebar, confirm the Ollama endpoint (http://localhost:11434) and pick a model (e.g. llava:latest). Click Test connection to populate the model dropdown.
  2. Type a criterion: e.g. blurry, dark, or accidental shots.
  3. Choose a scope (last N days / specific album / entire library). For a first try, scope to a small album.
  4. Click Start analysis. Photos stream into the grid with a colored badge (green = keep, red = flagged, yellow = failed).
  5. Click any photo to see the full image and the model's reason. Click Reveal in Photos to open Photos.app — the filename is copied to the clipboard so you can paste it into Photos' search.

Results are cached per (asset × prompt × model) under ~/Library/Containers/com.veli.badphotosout/Data/Library/Application Support/BadPhotosOut/cache.json, so re-running with the same settings is fast.

Out of scope

  • No automatic deletion or moving of photos.
  • No video analysis (images only).
  • No multi-photo / album-level reasoning — one photo per request.
  • No cloud LLMs — Ollama only.