Product / UX / Agent tools & protocols

Jina Reader

URL-to-LLM-input conversion service that turns any web page into clean, structured content optimized for language models. Prefix any URL with r.jina.ai to get markdown output. Simple, fast, and widely integrated into agent workflows as a lightweight alternative to full scraping tools. Open-source with 11K GitHub stars. Also offers search (s.jina.ai) and grounding capabilities.

Open-source branch of the r.jina.ai / s.jina.ai URL-to-markdown reader service; repo jina-ai/reader re-synced with the SaaS codebase Apr 2026 (MongoDB layer decoupled, local Docker deploy enabled). Confirmed live on GitHub June 2026.

Openness

5 high confidence

5.0

license: Apache-2.0(OSI)
source: public(TypeScript, stateless mode self-hostable via Docker)
managed-tier: r.jina.ai/s.jina.ai hosted SaaS (free tier + paid API key) on top of the same OSS core

Repo is Apache-2.0 with the full reader pipeline public and self-hostable; hosted Jina API is convenience hosting, not a gated core.

https://github.com/jina-ai/reader recorded 2026-06-04
Apache-2.0 license, public source, self-host Docker instructions, ~11k stars

Adoption

3 low confidence

3.0

No verified download or API-call volume found from a primary source. ~11k GitHub stars on the OSS repo plus a widely-used hosted r.jina.ai endpoint; capped at 3 on stars/reported-traction fallback in the absence of a measured usage figure.

https://github.com/jina-ai/reader recorded 2026-06-04
~11k stars, active maintenance (550 commits), production SaaS backing

Capability

3 medium confidence

3.0

Solid single-purpose reader/scrape tool with multi-format coverage and a search mode; mid-tier on the {coverage, freshness, structured output, rate limits} feature matrix vs full agentic browse/search platforms.

https://github.com/jina-ai/reader recorded 2026-06-04
feature list: HTML/PDF/Office/image input, markdown output, search mode, caching

Unchanged since 2026-06-09 (last edited, not re-checked)