chunky

Open-source toolkit for reliable RAG pipelines: convert PDFs to Markdown, clean documents, inspect chunks, compare chunking strategies, and enrich metadata for LLM applications.

GiovanniPasq/chunky

View on GitHub ↗

Open-source toolkit for reliable RAG pipelines: convert PDFs to Markdown, clean documents, inspect chunks, compare chunking strategies, and enrich metadata for LLM applications.

chunky grew +3.8% in the last 30 days, ranks 1084th of 1,535 in Memory & Knowledge (RAG), actively maintained, last commit 7 days ago.

Star trajectory

115 days tracked
2026-07-02189 stars today2026-10-25
Momentum

+3.8% in 30d, above the Memory & Knowledge (RAG) median of +0.9%.

Maintenance

Last commit 7 days ago, fresher than the median of 16d.

How it compares in Memory & Knowledge (RAG)

chunky
189
stars
+3.8% 30d
commit 7 days ago
Memory & Knowledge (RAG) median
382
stars
+0.9% 30d
commit ~16d ago
Leader · markitdown
192k
stars
+2.7% 30d
commit yesterday

Ranked 1084th of 1,535 by stars.

Language
Python
License
MIT License
Contributors
1
Forks
20
Watchers
3
Open issues
0
Releases
8
Created
2026-03-06
Stars this week
+3

You've seen where chunky stands today.

Get the moves before everyone else: the 5 Memory & Knowledge (RAG) repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain chunky?

Claim this page to add your own call-to-action.

Claim this page