AnsahMohammad/shots-studio

An AI Powered Screenshot manager for Android

What it solves

Screenshots quickly pile up into a chaotic gallery where finding a specific one by content is impossible. Shots Studio solves this by bringing AI-driven search, smart tagging, and collections to your screenshot folder, letting you find anything by what's inside the image, not just the file name.

How it works

Shots Studio scans your screenshots and uses AI to analyze their content. You can search for text, objects, or topics, and it will find matching screenshots. It can automatically generate tags for each screenshot using AI, and you can also add your own. You can group related screenshots into custom collections for quick navigation. AI processing can be done in two ways: by default it can send data to Google's Gemini API for cloud analysis, but you can switch to the on-device Gemma model so everything stays offline and nothing leaves your phone. To get started, you install the app, grant storage access, choose your AI mode (cloud needs an API key, offline doesn't), and tap the AI button to analyze and auto-tag.

Who it's for

Anyone who takes a lot of screenshots and struggles to find them later. It's especially useful for people who care about privacy and want AI features without sending their data to the cloud. Since it's open source, developers can also contribute to the project or modify it.

Highlights

  • AI-powered search by content (text, objects, topics)
  • Smart tagging: AI-suggested tags or manual
  • Collections to group related screenshots
  • Fully offline AI processing with the Gemma on-device model (no internet needed)
  • Choice of AI: on-device Gemma (private) or cloud Gemini 2.0 Flash / 2.5 Pro (speed or deep analysis)
  • Available on GitHub, Play Store, and F-Droid
  • 100% open source and community-driven

Related

  • Project
    Sentient-OS-Labs/sentient-os

    Sentient OS is an open‑source macOS personal AI that reads your local files, mail, calendar and messages, builds a Markdown knowledge base, and lets you hand off tasks via a shortcut. It can type, click, fill forms (Sidekick), draft replies in your voice (Double‑Tap), and surface proactive suggestions after overnight on‑device processing. You can run the built‑in model locally or plug in any compatible local or hosted LLM, and all raw data stays on your Mac unless you enable optional encrypted cloud sync.

  • Project
    framerslab/agentos

    AgentOS is a TypeScript framework for building LLM‑driven AI agents with persistent, neuroscience‑inspired memory, optional HEXACO personality, runtime tool‑forging, and full‑runtime “Generalized Mind Instances.” It supports 13 LLM providers, multi‑agent orchestration, RAG pipelines, guardrails, voice/telephony, and a large extension ecosystem, and it reports top open‑source memory benchmark scores.

  • Project
    Th0rgal/orb

    Orb is a macOS and iOS client that unifies access to local, private‑cloud, and provider‑hosted AI coding agents. It works with a self‑hosted Rust backend (sandboxed.sh) to store projects, missions, and coordinate remote execution, offering rich, resumable conversations and cross‑device sync.

  • Project
    Varnan-Tech/opendirectory

    A library of 64 pre-built agent skills that equip AI agents with expert-level domain knowledge for GTM, marketing, and growth tasks.