DigUp alternatives
DigUp alternatives in Data Collection & Preparation. Searches the files on your own computer by what is in them, photos, PDFs, audio, video and optional
Summary
DigUp alternatives in Data Collection & Preparation. Searches the files on your own computer by what is in them, photos, PDFs, audio, video and optional code, using EmbeddingGemma 2 on the machine. Nothing you index is uploaded. It is MIT-licensed, with downloads for Mac and beta builds for Windows and Linux. Free to use. 12 other catalog listings are linked below.
Alternatives
- ParseCrate — An open-source server that turns PDFs and Office files into Markdown, JSON, or HTML, with OCR, table detection, and chunks for retrieval
- Parser — Reads shipping papers, bills, receipts, and agreements, including files up to 1,000 pages, and returns JSON or a spreadsheet through an API
- Rerun — An SDK for logging, querying, and viewing the multimodal recordings physical-AI teams train on. The SDK is Apache-2.0 and stays free. Hub is
- Apify — A store of ready-made actors that fetch live web data for apps and agents, plus a place to run your own. The free plan includes $5 of usage
- Aylien — Provides AI-powered text analysis solutions, extracting insights from textual data.
- Browse AI — An automation tool that interacts with websites just like a human, enabling businesses to automate their web-based tasks.
- DataDoe — Connects an assistant to live Amazon seller, vendor, and ads data, and can carry out an action you ask for, such as a price change. The base
- Datalab.to — Parses PDFs, slides, and spreadsheets into markdown, HTML, or JSON, and can pull fields out with a schema.
- Deepgram — An AI-powered voice recognition and transcription service.
- localscreenshot — A screenshot API, MCP and CLI that captures a webpage for an agent, including phone and desktop layouts. The account includes 50 free
- Logimu — An API for Amazon product data and ranked search, from a warehouse or a live scrape, with an MCP connector. The entry plan is $19 a month
- Looti — An AI tool for extracting key information from documents.