{
  "id": 20928080,
  "title": "I tried replacing NotebookLM and Perplexity with one open-source research app, and it does more than just answer questions",
  "url": "https://urgent.news/2026/11/20/i-tried-replacing-notebooklm-and-perplexity-with-one-open-source",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-11-20T17:30:22.000Z",
  "source": {
    "name": "XDA Developers",
    "slug": "xda-developers",
    "url": "https://www.xda-developers.com/tried-replacing-notebooklm-perplexity-with-one-open-source-research-app-does-more-than-just-answer-questions/"
  },
  "original_language": "en",
  "account": "I recently tested NotebookLM and Perplexity as replacements with an open-source research application called SurfSense. While both NotebookLM and Perplexity excel at specific tasks, I found myself wishing for a tool that could combine their capabilities. That's where SurfSense comes in, offering a free, open-source solution that merges the best features of NotebookLM and Perplexity.\n\nUpon installation, SurfSense immediately presents an interface similar to NotebookLM, introducing users to various output options such as Markdown, Word, Slides, Spreadsheet, Web page, PDF, Mind map, Flashcards, Quiz, Podcast, Image, and Infographic. These options closely resemble NotebookLM's Studio panel, making it easy for users to navigate and utilize.\n\nWhat sets SurfSense apart is its open-source nature and privacy-focused design. Being open-source, the app's source code is publicly available on GitHub under the Apache 2.0 license, allowing users to inspect, modify, and contribute to its development. Additionally, SurfSense can operate entirely on a user's machine without requiring an account or cloud-based document storage. The app lets users choose the AI model powering the tool, providing flexibility in selecting local models like Qwen3 and Gemma 3, or connecting to cloud-based models.\n\nSurfSense supports a wide range of AI models for various tasks, including text generation, image generation, image editing, audio generation, and video generation. It also offers separate models for embedding, enabling the app to find relevant information within uploaded documents. Users can opt for local models to maintain privacy or choose cloud-based models for processing prompts and document excerpts.\n\nDuring my testing, SurfSense demonstrated impressive grounding capabilities, although not perfect. When asked about XDA, the app provided a generic answer despite not having specific information in its knowledge base. However, it performed well when summarizing a document, offering fast, well-formatted responses with citations. Clicking a citation opened the corresponding source in the Studio panel, highlighting the relevant passage.\n\nThe app's Studio outputs were also noteworthy. Users can select sources and customize prompts for outputs, generating mind maps, web pages, slides, and more. While flashcards, quizzes, and podcasts encountered issues during my testing, the app's primary strengths in combining NotebookLM and Perplexity's features make it a compelling alternative for researchers and knowledge workers seeking a privacy-focused, open-source research solution.",
  "summary": "Who needs two research apps when one can do both?",
  "key_points": [
    "SurfSense combines NotebookLM and Perplexity features in a free, open-source tool",
    "Users can choose AI models locally or connect to cloud-based models for flexibility",
    "App excels in grounding and summarizing documents, offering citation links in Studio outputs"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}