RAG & Knowledge
knowhere
Knowhere turns documents into structured, hierarchy-native chunks ready for agents and RAG.
★ 3.7k starsApache-2.0
View guide →LibreAI / RAG & Knowledge / SurfSense
// rag · MODSetter/SurfSense
SurfSense
SurfSense is an open-source rag & knowledge project by MODSetter (MODSetter/SurfSense on GitHub). It has 16,335 GitHub stars and 1,569 forks, is released under the Apache-2.0 license, and was last updated on GitHub on 7 October 2026.
Air-gapped, open-source NotebookLM alternative that turns local documents into briefings, decks and podcasts.
★ 16.3k stars⑂ 1.6k forksApache-2.0updated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- MODSetter/SurfSense
- GitHub stars
- 16,335
- Forks
- 1,569
- License
- Apache-2.0
- Last updated on GitHub
- 7 October 2026
- Category
- RAG & Knowledge
- Listing
- Full install guide
- Official site
- Official site
// how it works
How it works
- Decide if your documents must stay local
SurfSense fits when files are too sensitive to upload to a hosted notebook tool and you still want cited answers and finished artifacts from them.
- Download the desktop installer
Get the signed installer for Windows, macOS or Linux from the project's releases or download page; no Docker, terminal or account is required.
- Pick a model
Let the app pull a local model for you, or paste a base URL and key for any OpenAI-compatible API; keys are stored encrypted in your OS keychain.
- Add documents and open Studio
Drop in PDFs, Office files or images, ask cited questions, then open Studio to generate a briefing, deck, study guide or podcast from the same sources.
// features
Why people love it
Fully local, air-gapped operation
Parsing, chunking and embedding happen on your computer into a local SQLite index; the app uploads nothing and has no telemetry.
Cited answers over your files
Ask questions across all your documents and every answer cites the source it came from.
Studio artifact generation
Turn sources into summaries, flashcards, quizzes, mind maps, editable .pptx slides, .docx reports, .xlsx spreadsheets, HTML pages and PDFs.
Offline podcasts
Generate a two-host audio conversation from your documents, voiced offline by the bundled Kokoro-82M model.
Any OpenAI-compatible model
Use a local model the app downloads for you, or point SurfSense at any OpenAI-compatible endpoint, including your own local server.
Privacy controls by default
Outbound connections are off by default, with an egress panel listing every destination the app can reach so you choose what to enable.
Advertisement
// run it
Run it yourself
- Clone the repository
Clone the repo if you want the open-source Docker stack or to work on the code; most users simply download the desktop installer instead.
git clone https://github.com/MODSetter/SurfSense.git cd SurfSense - Download the desktop app
Install the signed desktop build for your platform from the releases page, which is the supported path in the README.
# Download SurfSense-Setup.exe / SurfSense-arm64.dmg / SurfSense.AppImage from GitHub Releases - see README for the exact link - Launch and choose a model
Open the app, let it pull a local model or add an OpenAI-compatible endpoint, then drop in your first documents.
# Launch SurfSense and follow the in-app model picker - see README for the exact command
// use cases
What you can build
- Studying from a term of lecture notes with flashcards, quizzes and mind maps generated locally.
- Briefing yourself from client or case papers that must never leave your machine.
- Turning interview transcripts and internal specs into a cited report or slide deck.
- Creating a two-host podcast summary of unpublished research to listen to offline.
Advertisement
// faq
Questions, answered
Who maintains SurfSense?
It is an open-source project by MODSetter and community contributors, with a Discord and GitHub Discussions for support and direction.
Is SurfSense free?
The app and its updates are free and the code is Apache-2.0 licensed. The README notes an optional licence that adds plugins and priority support but gates nothing else.
Does it need a paid API key?
No. Every role can run locally: you can let the app download a local model and work with no account or API key, or optionally bring your own OpenAI-compatible key.
How does it compare with Google NotebookLM?
Both produce summaries, flashcards, quizzes, mind maps and audio overviews, but SurfSense runs offline on your machine with your choice of model, while NotebookLM uploads sources to Google and uses Gemini only.
How do I get started?
Download the installer for your platform, pick a model in the app, drop in documents, and ask your first cited question - no terminal or Docker needed.
// keep exploring
Similar tools
RAG & Knowledge
insights-lm-public
Self-hosted NotebookLM alternative — chat with documents, get audio summaries.
★ 656 starsMIT
View guide →RAG & Knowledge
MinerU
MinerU — turns PDFs and Office documents into LLM-ready Markdown and JSON for agents and RAG pipelines, Apache-2.0 plus terms
★ 82.5k starsApache-2.0 + terms
View guide →RAG & Knowledge
linkly-ai-skills
Skills that let coding agents search and read your local documents.
★ 65 starsApache-2.0
View guide →RAG & Knowledge
OpenKB
OpenKB compiles your documents into a persistent, interlinked wiki knowledge base — no vector DB
★ 4.8k starsApache-2.0
View guide →RAG & Knowledge
KnowNote
A local-first AI knowledge base and NotebookLM replacement built with Electron.
★ 1.2k starsGPL-3.0
View guide →// alternatives
Alternatives in RAG & Knowledge
The most-starred other RAG & Knowledge projects in the LibreAI catalogue — the realistic shortlist if SurfSense 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 SurfSense — keep exploring the shelf either side of it.
- turbovec★ 17.4k
A blazing-fast vector index in Rust, built on TurboQuant - with Python bindings
- zvec★ 16.1k
Lightweight, lightning-fast in-process vector database from Alibaba that embeds in your app.
- DocsGPT★ 18.3k
A private AI platform for agents, assistants and enterprise search over your documents
- llmware★ 14.8k
Unified framework for enterprise RAG pipelines with small, specialized models - local, private and secure.
- DB-GPT★ 20.1k
An agentic AI data assistant - chat with your databases, run SQL and code, get reports
- QAnything★ 14.2k
Local knowledge-base Q&A over PDFs, Office files, images and web pages - offline and CPU-friendly.
Get SurfSense
Free and open — grab the source, star the repo, and start creating.