HKUDS/RAG-Anything

★24,676Python🇨🇳 Greater ChinaMIT⑂ 2,894Issue 79Updated Nov 17, 2026

"RAG-Anything: All-in-One RAG Framework"

Unified RAG Pipeline That Treats Text, Tables, and Images as One — RAG-Anything extends LightRAG into a multimodal retrieval-augmented generation framework that parses documents containing text, images, tables, and equations into a unified knowledge structure. Backed by a research paper, it targets developers who need RAG over heterogeneous, real-world documents rather than plain text alone.

LLMs & MLmulti-modal-ragretrieval-augmented-generation

Metrics

Relative growth (7d)+1%Growth over the last 7 days relative to size
Acceleration+106%Change in growth pace from the week before
Attention47The three metrics scaled to 0–100 and combined

Retention can be computed 30 days after a repository first trends (it isn't shown until then). See About for how each metric is defined.

Star growth and Trending appearances (last 30 days)

First listed+71★/dayDaily
Oct 22, 2026Nov 20, 2026

Bands mark days on the trending list (darker = higher rank)

Daily trending ranks as a table (1 days)
DateDaily
Nov 18, 2026
python #12 +17

Created Jun 6, 2025 · First on trending Nov 18, 2026

Other notable repositories in the same category (LLMs & ML)

See all LLMs & ML repositories →

Rank within retrieval-augmented-generation

#Repository★
1infiniflow/ragflow94,456
2VectifyAI/PageIndex40,492
3stanford-oval/storm31,912
4HKUDS/RAG-Anything24,676
5memvid/memvid17,433
6neuml/txtai13,656
7simular-ai/Agent-S13,009
8Marker-Inc-Korea/AutoRAG6,080
9snap-stanford/memorilla1,537
10dukesun99/Corpus2Skill96

See all retrieval-augmented-generation repositories →

Get the weekly digest by email

Every Monday: the repositories that grew most last week, and how the buzz spread between the global and Japanese-language web. Unsubscribe any time. See the privacy and ad policy for how we handle your address.