head to head · open source
AutoRAG vs document.ai
AutoRAG has 5,848 GitHub stars, 511 forks, 98 open issues and last shipped 2 days ago. document.ai has 3,658 stars, 321 forks, 1 open issues and last shipped today. AutoRAG leads on adoption by 60% (5,848 vs 3,658 stars). AutoRAG is written in TypeScript under Apache-2.0; document.ai is written in Python under AGPL-3.0. AutoRAG has attracted 9% as many forks as stars, document.ai 9%. document.ai was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 2 topic tags (knowledge-base, llm), 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.
← all 20902 open source comparisons
Side by side
| AutoRAG | document.ai | |
|---|---|---|
| GitHub stars | ★ 5.8K | ★ 3.7K |
| License | Apache-2.0 | AGPL-3.0 |
| Written in | TypeScript | Python |
| Last push | 2026-11-14 | 2026-11-16 |
| Forks | ⑂ 511 | ⑂ 321 |
| Self-hosting | Yes | Yes |
| Data ownership | Your server | Your server |
pick AutoRAG if
- You weight community size — 5.8K stars and counting
- You want the Apache-2.0 license terms
- Your stack matches TypeScript
- You value the larger contributor base for long-term maintenance
pick document.ai if
- You want the document.ai feature set and don't need the biggest community
- You prefer the AGPL-3.0 license terms
- Your stack matches Python
- You evaluated both and document.ai fits your workflow better
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 →
About document.ai
document.ai · EAER 可溯源、带时效判断的企业知识库问答。 用户不仅得到答案,还能看到答案来自哪份文档的哪个版本、哪一处,以及这条依据在问题关心的那一天是否有效。制度会修订、会作废、会被补充通知覆盖,“查到一段相似的话”不等于“答对了”;EAER 把版本、有效期、权限和验证当作问答本身的一部分来做。 document.ai 2023 年的版本(向量数据库 + GPT 3.5 的本地知识库方案与 MSD 医疗问答示例)保留在 legacy/ ,对应的提交打了标签 msd demo 2023 。 能做什么 三种执行模式。 Fast 一次检索直接作答;Deep 按计划模板(比较、多跳、因果)分步检索;Verified 在作答后做语义检查与定向补检索。Router 按问题选入口,证据不足时逐级升级,预算用尽仍无法确认就拒答。 验证层。 代码做确定性检查:引用的证据是不是本次检索到的、用户有没有权限、定位与原文是否对得上、数值与日期是否出现在证据里、证据在目标时间是否有效;模型只判断证据是否真正支持结论。拿不准的标“未验证”,不支持的删除,核心结论不过则整题拒答并说明缺少什么。 三类时间查询。 当前生效;某天实际生效(按有效期);截至某天系统所知(回溯,按审核通过时间,有效期取当时记录的值)。生效日的来源分正文写明、推断、未知三级,如实标注。 文档生命周期。 上传 → 审核(逐份或批量,可补录更正)→ 可搜索 →…
read the full document.ai 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 AutoRAG or document.ai more popular?
AutoRAG has 5,848 GitHub stars and document.ai has 3,658. AutoRAG has the larger community by that measure.
Are AutoRAG and document.ai free?
Both are open source. AutoRAG is licensed under Apache-2.0 and document.ai under AGPL-3.0. Neither carries a licence fee.
What is the difference between AutoRAG and document.ai?
AutoRAG is written in TypeScript and document.ai in Python. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.
Which should I choose, AutoRAG or document.ai?
Choose AutoRAG if you want the larger community (5,848 stars) or its Apache-2.0 licence terms. Choose document.ai if its feature set, stack or AGPL-3.0 licence fits better. Both are self-hostable.