# jina-ai/reader

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

Repository: https://github.com/jina-ai/reader
Canonical: https://ross.abutalabs.com/products/reader
Homepage: https://jina.ai/reader
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: llm, proxy
Last push: 2026-05-22T02:56:46+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 83, release rhythm 35, longevity 62
- inputs: {"age_days": 875, "days_push": 103, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 11912, forks 876 (observed 2026-08-28T04:10:50.479843+00:00)

## What it is
Jina AI Reader converts any URL into LLM-friendly markdown via the r.jina.ai prefix, and searches the web into markdown via s.jina.ai. It renders pages with headless Chrome or curl-impersonate, parses PDFs and Office documents, and can be self-hosted in stateless mode with optional S3-compatible caching.

## Use cases
- convert web pages to markdown for LLM input
- feed clean page content into RAG pipelines
- search the web and get results as markdown for agents
- parse PDFs into LLM-readable text
- give LLM agents access to up-to-date web knowledge
- self-host a URL-to-markdown reader service

## When to choose
- you need clean, LLM-friendly text extracted from arbitrary URLs
- you're building RAG or agent systems that need web content or search results
- you want a hosted API with a simple URL-prefix interface, or a self-hostable equivalent

## When to avoid
- you only need simple static HTML fetching without rendering or cleaning
- you need the MongoDB-backed SaaS storage layer, which is not included in the open-source branch
- you need heavy scraping at scale without rate limits

## Facets
- artifact type: service
- maturity: active
- function: web-scraping, proxy, rag, search-engine, pdf, llm-inference
- domain: large-language-models, crawlers, web-development
- platform: self-hosted, cloud
- tags: url-to-markdown, llm-friendly-input, web-reader, serp, headless-chrome, mcp-server, jina-ai, retrieval-augmented-generation, search, nodejs, docker, web-server

## Member repositories
- jina-ai/reader (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:50.479843+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 2026-08-29T17:15:12.898496+00:00, confidence not recorded.
  - readme: https://github.com/jina-ai/reader (fetched 2026-08-28T04:10:50.479843+00:00, sha 0b012a50136b)
  - homepage: https://jina.ai/reader (fetched 2026-08-29T08:13:15.418609+00:00, sha 0b3c5268759a)
  - site_page: https://api.jina.ai/scalar (fetched 2026-08-29T08:13:15.428618+00:00, sha 196874487239)
- Data as of 2026-08-30T08:39:29.467469+00:00.