snapsearch

Your Mac screenshots folder is a disaster. This fixes it — with vision, embeddings, and semantic search.

An AI agent + custom MCP server that sees your screenshots, understands what's in them, organizes them into clean folders, and lets you find anything with natural language.

Fully local. No cloud uploads. No subscriptions.

✨ Features

• Context-Aware Organization: Unlike scripts that blindly rename files, this agent understands context and categorizes intelligently.
• Semantic Search: Find screenshots by meaning (e.g., "that slack message about the deploy"), even with garbage filenames.
• Adaptive: Tell it to "actually split design into figma vs other" and it re-organizes on the fly.
• Persistent Memory: Decisions are remembered across sessions using a local ChromaDB.

🚀 Quickstart (No Clone Needed!)

Using uvx (the modern Python alternative to npx), you can run snapsearch instantly without manual cloning or pip installs.

1. Set your Environment Variables

You need to provide your OpenAI API key and optionally your screenshots directory. You can set them in your environment:

export OPENAI_API_KEY="sk-..."
export SCREENSHOTS_DIR="/Users/yourname/Desktop" # Optional, defaults to ~/Desktop/screenshots-demo

2. Run the Agent

Trigger the autonomous organizer right away with these commands:

# Full auto-organize (scan → vision → embed → move → rename)
uvx snapsearch

# Semantic search queries
uvx snapsearch "find my react error screenshots"
uvx snapsearch "show me figma mockups from last month"
uvx snapsearch "that slack conversation about the deployment"

# Partial organize
uvx snapsearch "organize only the code screenshots"

# Index health check
uvx snapsearch --stats

🤖 How it works

Behind the scenes, snapsearch builds a powerful pipeline to understand your images:

1. 🖼️ screenshot.png
2. 👁️ GPT-4o vision → "React error about invalid hook call in App.js, line 23"
3. 🔢 text-embedding-3-small → [0.021, -0.847, 0.334, ...]
4. 💾 ChromaDB (local) → Stored permanently on disk
5. 🔍 search("hooks problem") → Finds it instantly!

The Resulting Organization

Your chaotic screenshots folder turns into a clean, categorized structure:

• 📂 ~/Screenshots/
  • 📁 code/
    • 📁 errors/
      • 📄 react-hooks-invalid-call.png
      • 📄 python-importerror-requests.png
    • 📁 snippets/
      • 📄 vim-config-lsp-setup.png
  • 📁 design/
    • 📁 figma/
      • 📄 darkmode-mobile-v3.png
    • 📁 other/
      • 📄 canva-instagram-post.png
  • 📁 chats/
    • 📄 whatsapp-trip-planning-march.png
  • 📁 docs/
    • 📄 notion-q2-sprint-board.png
  • 📁 memes/
    • 📄 drake-hotline-bling-coding.png
  • 📁 web/
    • 📄 vercel-deployment-dashboard.png

🛠️ Architecture

• 🤖 snapsearch (Agent)
  • 🔌 Connects via MCPServerStdio to:
  • ⚙️ snapsearch-mcp (MCP server — 8 tools)
    • 👁️ vision.py — GPT-4o vision to structured descriptions
    • 🧠 embeddings.py — OpenAI embeddings & ChromaDB operations
    • 🧱 models.py — Pydantic data models

MCP Tools Available

🔌 Use in Claude Desktop (MCP server only)

Because it's distributed on PyPI, using it in Claude Desktop is extremely simple.

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "snapsearch": {
      "command": "uvx",
      "args": ["snapsearch-mcp"],
      "env": {
        "SCREENSHOTS_DIR": "/Users/yourname/Desktop",
        "OPENAI_API_KEY": "sk-..."
      }
    }
  }
}

🔒 Privacy & Data

🏗️ Stack

• MCP server — mcp Python SDK v1.27+
• Agent — OpenAI Agents SDK v0.17+
• Vision — gpt-4o (low detail mode — fast + cheap)
• Embeddings — text-embedding-3-small
• Vector DB — ChromaDB (local, persistent)
• Validation — Pydantic v2

📄 License

MIT