Product
QAnything
QAnything is an open-source AI app, launched in 2024, made for developers and businesses.
A local knowledge-base Q&A system from NetEase Youdao that reads many file formats.
Main jobs: Ask your documents, Knowledge base (RAG). It is open source and free to use. You can use it on your own server, offline on your own machine and through an API.
Markdown version of https://godooo.ai/en/product/qanything. Every page on this site has one: add .md to its address.
At a glance
- Type
- Product
- Launched
- 2024
- Galaxy
- Agents & Automation
- Pricing
- Open source, free
- Open source
- Yes · AGPL-3.0
- Source code
- github.com/netease-youdao/QAnything
- GitHub stars
- 14,190
- How you run it
- Self-host · Runs offline · API
- Made for
- Developers · Businesses
- Website
- qanything.ai
- Also known as
- 有道 QAnything
What it can do
Ask your documentsmain jobunconfirmed
“With QAnything , you can simply drop any locally stored file of any format and receive accurate, fast, and reliable answers.”— github.com, 2026-09-24
Knowledge base (RAG)main jobunconfirmed
“QAnything ( Q uestion and A nswer based on Anything ) is a local knowledge base question-answering system designed to support a wide range of file formats and databases, allowing for offline installation and use.”— github.com, 2026-09-24
Build a chatbotsupportedunconfirmed
“Supports a quick start mode similar to Kimi, fileless chat mode, retrieval mode only, custom Bot mode.”— github.com, 2026-09-24
Document parsingsupportedunconfirmed
“Currently supported formats include: PDF(pdf) , Word(docx) , PPT(pptx) , XLS(xlsx) , Markdown(md) , Email(eml) , TXT(txt) , Image(jpg，jpeg，png) , CSV(csv) , Web links(html) and more formats coming soon…”— github.com, 2026-09-24
Vector searchsupportedunconfirmed
“Supports massive data question and answer, two-stage vector sorting, solves the problem of degradation of large-scale data retrieval”— github.com, 2026-09-24
unconfirmedproposed by a machine, awaiting calibration
Alternatives
- RAGFlowOpen source, freeAlso does: Ask your documents, Document parsing, Knowledge base (RAG)
- kotaemonOpen source, freeAlso does: Ask your documents, Knowledge base (RAG), Build a chatbot; no code needed
- AnythingLLMOpen source, freeAlso does: Ask your documents, Knowledge base (RAG), Build a chatbot; no code needed
- PrivateGPTOpen source, freeAlso does: Ask your documents, Knowledge base (RAG), Document parsing
- LlamaIndexOpen source, freeAlso does: Knowledge base (RAG), Ask your documents, Document parsing
- KhojOpen source, freeAlso does: Ask your documents, Knowledge base (RAG); no code needed
- Langchain-ChatchatOpen source, freeAlso does: Ask your documents, Knowledge base (RAG)
- MaxKBOpen source, freeAlso does: Build a chatbot, Knowledge base (RAG), Ask your documents; no code needed
- FastGPTOpen source, freeAlso does: Build a chatbot, Knowledge base (RAG), Document parsing; no code needed
- LightRAGOpen source, freeAlso does: Knowledge base (RAG), Ask your documents, Vector search
- NotebookLMFree plan + paid upgradesAlso does: Ask your documents, Knowledge base (RAG); no code needed
- DifyOpen source, freeAlso does: Build a chatbot, Knowledge base (RAG); no code needed
Connections
Questions
What is QAnything?
QAnything is an open-source AI app, launched in 2024, made for developers and businesses. A local knowledge-base Q&A system from NetEase Youdao that reads many file formats.
Is QAnything free?
Yes. QAnything is open source (AGPL-3.0) and free to use.
Is QAnything open source?
Yes, under the AGPL-3.0 license. The source code is at https://github.com/netease-youdao/QAnything.
Can QAnything run locally?
Yes. QAnything can run offline on your own machine. It can also be self-hosted on your own server.
What can QAnything do?
Main jobs: Ask your documents, Knowledge base (RAG). It can also do: Build a chatbot, Document parsing, Vector search.
What are open-source alternatives to QAnything?
Open-source ones: RAGFlow, kotaemon, AnythingLLM, PrivateGPT, LlamaIndex, Khoj, Langchain-Chatchat and MaxKB. Others: NotebookLM.
Sources
- github.com/netease-youdao/QAnythingchecked 2026-09-24
- qanything.ai