head to head · open source

OpenViking vs AutoRAG

OpenViking has 42,289 GitHub stars, 3,494 forks, 999 open issues and last shipped today. AutoRAG has 5,848 stars, 511 forks, 98 open issues and last shipped 2 days ago. OpenViking leads on adoption by 623% (42,289 vs 5,848 stars). OpenViking is written in Python under AGPL-3.0; AutoRAG is written in TypeScript under Apache-2.0. OpenViking has attracted 8% as many forks as stars, AutoRAG 9%. OpenViking was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 3 topic tags (agentic-rag, knowledge-base, memory), so they are genuine substitutes rather than adjacent tools.

Two open source projects, one decision. Both are free and self-hostable — the differences are community size, license terms, language stack and release pace.

OpenViking ★ 42K AutoRAG ★ 5.8K category Content & Publishing

← all 20902 open source comparisons

Side by side

OpenViking AutoRAG
GitHub stars ★ 42K ★ 5.8K
License AGPL-3.0 Apache-2.0
Written in Python TypeScript
Last push 2026-11-16 2026-11-14
Forks ⑂ 3.5K ⑂ 511
Self-hosting Yes Yes
Data ownership Your server Your server

pick OpenViking if

  • You weight community size — 42K stars and counting
  • You want the AGPL-3.0 license terms
  • Your stack matches Python
  • You value the larger contributor base for long-term maintenance

full OpenViking profile →

pick AutoRAG if

  • You want the AutoRAG feature set and don't need the biggest community
  • You prefer the Apache-2.0 license terms
  • Your stack matches TypeScript
  • You evaluated both and AutoRAG fits your workflow better

full AutoRAG profile →

About OpenViking

The Context Database for AI Agents English / 中文 / 日本語 Website · Live Demo · GitHub · Issues · Docs · Blog Lark · WeChat · Discord · X What is OpenViking OpenViking is an open source context database for AI agents — one filesystem for everything an agent knows: knowledge, memory, and skills. Most agent memory is a black box: text goes in, embeddings come out, and nobody can see what was actually stored. OpenViking organizes context as a virtual filesystem under viking:// instead. Agents navigate it like files — ls , tree , read , write , grep — and you can open any directory to inspect and edit what your agent…

read the full OpenViking overview →

About AutoRAG

AutoRAG Agent Your personal librarian agent: it finds, reads, and cites anything on your computer. = 24" / = 1.2" / Dazzi: the AutoRAG desktop app Dazzi is the app version of AutoRAG Agent. Download it for Mac and Windows at dazziapp.com , or build from NomaDamas/AutoRAG app. It is a real file manager with the AutoRAG engine in this repository behind it. Fast file search. Hybrid keyword + meaning search with a reranker finds files by what is inside them, and every answer links the passage it came from. Messengers, mail, and more. Slack, KakaoTalk, Discord, Telegram, WhatsApp, every inbox you sign in to, GitHub…

read the full AutoRAG overview →

More in Content & Publishing

Related comparisons

More Documentation & Knowledge Base projects

Compare either of these against the rest of the Documentation & Knowledge Base field.

Frequently asked questions

Is OpenViking or AutoRAG more popular?

OpenViking has 42,289 GitHub stars and AutoRAG has 5,848. OpenViking has the larger community by that measure.

Are OpenViking and AutoRAG free?

Both are open source. OpenViking is licensed under AGPL-3.0 and AutoRAG under Apache-2.0. Neither carries a licence fee.

What is the difference between OpenViking and AutoRAG?

OpenViking is written in Python and AutoRAG in TypeScript. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.

Which should I choose, OpenViking or AutoRAG?

Choose OpenViking if you want the larger community (42,289 stars) or its AGPL-3.0 licence terms. Choose AutoRAG if its feature set, stack or Apache-2.0 licence fits better. Both are self-hostable.