# lumina-ai-inc/chunkr

Vision infrastructure to turn complex documents into RAG/LLM-ready data

Repository: https://github.com/lumina-ai-inc/chunkr
Canonical: https://ross.abutalabs.com/products/chunkr
Homepage: https://chunkr.ai
Language: Rust
License: AGPL-3.0
License Family: copyleft
Last push: 2026-04-09T22:53:39+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 76, release rhythm 29, longevity 52
- inputs: {"age_days": 739, "days_push": 146, "days_rel": 398, "gap_med": 0, "n_releases_24m": 118}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4137, forks 275 (observed 2026-08-28T04:08:36.222680+00:00)

## What it is
Chunkr is an open-source document intelligence API that performs layout analysis, OCR, and semantic chunking to convert PDFs, presentations, Word documents, and images into RAG/LLM-ready structured data. It is a production-ready service deployable via Docker Compose, with a separate managed cloud API offering proprietary models.

## Use cases
- parse pdfs into rag-ready chunks
- extract structured text from scanned documents with ocr
- convert word docs and powerpoints for llm ingestion
- chunk complex documents semantically for vector search
- self-host a document parsing pipeline
- get bounding boxes and layout structure from documents

## When to choose
- you need to feed complex documents into RAG or LLM pipelines
- you want a self-hosted, production-ready document parsing service
- you need OCR plus layout analysis with structured HTML/Markdown output

## When to avoid
- you need maximum parsing accuracy without infrastructure work - the managed cloud API uses proprietary in-house models
- you need a permissive license - the open-source version is AGPL-3.0
- you only need simple plain-text extraction from clean PDFs

## Facets
- artifact type: service
- maturity: active
- function: ocr, parser, rag, machine-learning, pdf, api-framework
- domain: artificial-intelligence, pdf, developer-tools
- platform: self-hosted, rust, python
- tags: document-intelligence, layout-analysis, semantic-chunking, document-parsing, llm-data-preparation, vision-language-models, retrieval-augmented-generation, natural-language-processing, docker, web-server

## Member repositories
- lumina-ai-inc/chunkr (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:36.222680+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:23:00.849639+00:00, confidence not recorded.
  - readme: https://github.com/lumina-ai-inc/chunkr (fetched 2026-08-28T04:08:36.222680+00:00, sha c662864c1e35)
  - homepage: https://chunkr.ai (fetched 2026-08-29T09:14:02.556396+00:00, sha 5ac3f2ff6068)
- Data as of 2026-08-30T08:39:29.467469+00:00.