LibreAI / RAG & Knowledge / reader-source
// rag · Marvy101/reader-source

reader-source

reader-source is an open-source rag & knowledge project by Marvy101 (Marvy101/reader-source on GitHub). It has 58 GitHub stars and 3 forks, is released under the MIT license, and was last updated on GitHub on 29 September 2026.

Self-hosted rag & knowledge: open-source native macos ai reading workspace for pdf.

💎 Hidden gem★ 58 stars⑂ 3 forksMITupdated 2026-09
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
// project facts

Project facts

GitHub stars
58
Forks
3
License
MIT
Last updated on GitHub
29 September 2026
Listing
Hidden gem — a shorter page for a lesser-known project
Official site
Official site
// how it works

How it works

  1. Clone the repository

    Fetch the source code onto your machine.

  2. Open the project

    Load the Xcode project or download a release.

  3. Build and run

    Compile in Xcode with Cmd+R.

  4. Configure as needed

    Adjust settings in the app preferences.

// features

Why people love it

Ai

Built around ai for a focused workflow.

Annotations

Built around annotations for a focused workflow.

Books

Built around books for a focused workflow.

Epub

Built around epub for a focused workflow.

Open source

Inspect, fork, and modify every line of the code.

Self-hosted

Run it on your own machine — no account lock-in.

Advertisement
// run it

Run it yourself

  1. Clone

    Get the source on your machine.

    git clone https://github.com/Marvy101/reader-source.git
  2. Open

    Load in Xcode.

    cd reader-source && open reader-source.xcodeproj
  3. Build

    Compile from the terminal.

    xcodebuild -scheme reader-source -configuration Release build
// use cases

What you can build

  • Learning how a real rag & knowledge project is built
  • Prototyping ideas quickly from working code
  • Teaching or studying rag & knowledge patterns
  • Self-hosting instead of paying for SaaS
Advertisement
// faq

Questions, answered

What does reader-source do?

It open-source native macOS AI reading workspace for PDF, EPUB, and TXT with highlights, notes, book chat, and local-first storage. Download: reader.marvy101.com/download, giving you a working starting point you can run and adapt.

Is reader-source free to use?

Yes — the code is open-source, so you can use and modify it without a license fee.

How do I install reader-source?

Clone the GitHub repository and follow the README; the typical flow is install dependencies, configure, and run.

What is reader-source written in?

It is primarily written in Swift, so you will need that toolchain to build or extend it.

Where can I get help with reader-source?

The GitHub repository is the hub: open issues for bugs and check the README and discussions for guidance.

// keep exploring

Similar tools

RAG & Knowledge

uxie

PDF reader with AI chat, flashcards, annotations, and text-to-speech.

★ 197 starsCustom
View guide →
Dev Tools

mira

Self-hosted AI code reviewer — PR walkthroughs, vuln scanning, custom rules.

★ 356 starsApache-2.0
View guide →
Automation

sim

Sim is the collaborative workspace to build, deploy, and monitor AI agents and workflows. Used by 100,000+ builders.

★ 29.8k starsApache-2.0
View guide →
RAG & Knowledge

textbook-to-note

Self-hosted rag & knowledge: turn your own pdf textbooks into an ai-searchable knowl.

★ 104 starsMIT
View guide →
RAG & Knowledge

uteke

Self-hosted rag & knowledge: 🧠 the brain for your ai — local-first memory engine for.

★ 268 starsApache-2.0
View guide →
RAG & Knowledge

docs-mcp

Self-hosted rag & knowledge: cometchat docs search + implementation bundles: add cha.

★ 97 starsApache-2.0
View guide →
// alternatives

Alternatives in RAG & Knowledge

The most-starred other RAG & Knowledge projects in the LibreAI catalogue — the realistic shortlist if reader-source is not the right fit.

  • MarkItDown★ 193.5k

    MarkItDown — Microsoft tool that converts PDFs, Office files, images and more to clean Markdown for LLMs, MIT

  • Dify★ 157.8k

    Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or…

  • ragflow★ 91.6k

    RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context…

  • PaddleOCR★ 90.8k

    Lightweight OCR toolkit turning PDFs and images into structured, LLM-ready data in 100+ languages

  • MinerU★ 82.5k

    MinerU — turns PDFs and Office documents into LLM-ready Markdown and JSON for agents and RAG pipelines, Apache-2.0 plus terms

// more in rag

More in RAG & Knowledge

Nearby RAG & Knowledge projects in the catalogue, closest in stars to reader-source — keep exploring the shelf either side of it.

  • linkly-ai-skills★ 65

    Skills that let coding agents search and read your local documents.

  • KDAN-PDF-MCP★ 57

    MCP server that lets Claude and ChatGPT edit and compare PDFs.

  • tela★ 73

    A self-hostable markdown team wiki with a built-in MCP server.

  • qdrant-loader★ 55

    Free rag & knowledge tool that enterprise-ready vector database toolkit for building s.

  • omnigram★ 75

    A Flutter e-reader and audiobook app with AI chat.

  • InsightPDF★ 49

    Chat with PDFs and see exactly where each answer was found.

Get reader-source

Free and open — grab the source, star the repo, and start creating.