Skip to content
English

Switch theme

Discover▾

Not sure where to start? This week’s hottest software, models and stacks in three minutes.

AI Apps▾

AI software people use: from assistants like ChatGPT to tools for coding, video and workflows, picked by purpose.

For Agents▾

Software for AI: tools that let your agent (Claude Code, Codex, Cursor…) browse, read docs, run code and remember.

Models▾

Choose models, estimate cost, self-host: prices, rankings, benchmarks, free tiers and compute.

Solutions▾

A goal or an error message? Ready-made stacks, steps and fixes by scenario.

Learn▾

A systematic course from zero to the frontier, with an algorithm library, must-read papers and tutorials.

Frontier▾

Daily AI news, weekly highlights, the latest papers and how AI is changing every discipline.

// I want to solve · Individuals / Researchers / Students

🧠 Personal knowledge base: AI that answers from my files

Collect notes, PDFs and web pages in one place and have AI answer only from them with citations, either in the cloud (NotebookLM etc.) or fully local.

5 steps5 alternatives2 stacks · 1 problemschecked 2026-10-22

How to do it

  1. 01Decide whether your files may go to the cloud: if yes, use NotebookLM or your notes app’s AI; if not, go local
  2. 02Cloud: create a NotebookLM notebook per topic, add PDFs, pages and docs, and check the cited passages in answers
  3. 03Local: install Ollama + Open WebUI (or AnythingLLM desktop) and add documents to a knowledge base
  4. 04Convert scanned or complex PDFs to Markdown first (MarkItDown, Docling); retrieval improves a lot
  5. 05Save common questions as templates, e.g. “summarise as a timeline”, “list contradictory claims”

What it costs

Free start

NotebookLM is free to use; Obsidian is free; the local route is all open source

Individual paid

Notion AI, higher NotebookLM limits etc. roughly $8–20/mo (see sites); Google AI Pro $19.99/mo includes higher limits

Team / enterprise

Many users with permissions: see the enterprise private AI scenario

Prices change; the vendor’s official page wins. Subscriptions compared · API prices

Alternatives: which to pick

OptionChoose it when
NotebookLM（Gemini Notebook）Easiest, answers cite your sources
Obsidian + AI 插件Notes stay local as Markdown long-term
Notion AIYour team already uses Notion
AnythingLLMA single desktop app for a local knowledge base
Open WebUI + OllamaFully local and multi-user

✓ Good fit

  • Q&A and summaries over papers, course material, reading notes and work docs

✗ Not a good fit

  • Large daily updates and departmental permissions: use enterprise RAG

Ready-made stacks

All stacks
Personal knowledge base Capture notes, web pages and PDFs into a searchable second brain that AI can answer from. 3 tools Local private knowledge baseBeginner Documents never leave your machine: a local model answers and a local vector store retrieves. Good for individuals and small teams turning PDFs and notes into a Q&A knowledge base. 4 tools

Software that helps

All software
NotebookLM AI notes & knowledge management Google's source-grounded notebook for Q&A, summaries and audio overviews. Closed / commercial Freemium WebiOSAndroid Obsidian AI notes & knowledge management Local Markdown notes and personal knowledge base; plugins connect AI and agents. Closed / commercial Freemium macOSWindowsLinux Notion AI notes & knowledge management Workspace combining docs, knowledge base and AI agents. Closed / commercial Freemium WebmacOSWindows siyuan AI notes & knowledge managementv3.8.8 ★ 47k Privacy-first self-hosted knowledge workspace for humans and agents. Open source WindowsmacOSLinux anything-llm AI apps & chat clientsv1.17.0 ★ 67k Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience Open source API khoj AI apps & chat clients2.0.0-beta.28 ★ 38k Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free. Open source API open-webui AI apps & chat clientsv0.11.4 ★ 156k User-friendly AI Interface (Supports Ollama, OpenAI API, ...) Open source API Ollama Local inference & servingv0.40.8 ★ 184k Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. Open source CLIAPI MarkItDown Document parsing & web scrapingv0.1.9 ★ 191k Microsoft tool converting office documents to Markdown for LLMs. Open source CLIPythonSDK PDFMathTranslate Document parsing & web scraping ★ 38k PDF scientific paper translation that preserves layout. Open source localWeb

Problems & solutions

All problems

Needs in this scenario

  • DEV-03RAG parsing, chunking and retrieval are inaccurate

    Developers · People search for: best pdf parser for rag; docling vs markitdown; rag retrieval accuracy

Official references

Compiled from official documentation on 2026-10-22; not reproduced in our own environment. Follow the official docs if they differ.

Data updated: Solutions & stack guides(UTC+8)