Updated

R2R

SciPhi's open-source retrieval system for agentic RAG, served as a REST API, with multimodal ingestion, hybrid search and knowledge graphs (MIT licence). It has had no release since mid-2025, and its hosted site and docs are offline.

1 open-source project declares R2R in their code; no maker's live product we track uses it yet.

Open sourceSelf-hostable

In maintenance: Apparently abandoned, not announced. Last GitHub release v3.6.5 on 6 June 2025, last PyPI release 3.6.6 on 17 August 2025, last commit on 7 November 2025. sciphi.ai fails to connect and the R2R docs return 404. The repository is not archived. Source ↗

Profile checked

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

How makers use R2R

What R2R is used for

Document Parsing · Open-source library + hosted API →A self-hosted agentic RAG server with ingestion, hybrid search and knowledge graphs behind a REST API.Trade-off: No release since mid-2025 and its hosted site and docs are offline; apparently abandoned.
Reducto11Unstructured1Carbon1Docling0MarkItDown0R2R0Makers' products on each, for document parsing

R2R vs the alternatives makers chose

OptionMakers' productsOpen source
Reducto11 85%No
Carbon1 8%No
Unstructured1 8%Yes
R2R0 0%Yes

For document parsing: how many of the 13 makers' products we know the document parsing of chose each option.

When to use R2R, and when not

Something else fits better if

  • You only need the text out of born-digital PDFs, fast and free: pypdf or pdf-parse or PyMuPDF.
  • You want Markdown from many file types with one local tool: MarkItDown or Docling.
  • Layout and tables matter and documents must stay on your own machines: Docling or Marker.
  • Your inputs mix PDFs, emails, HTML and office files and you may move to a hosted API later: Unstructured.
  • Scans, dense tables or forms where a parsing error means a wrong answer: Reducto or LlamaParse or Mistral AI.
From each decision's guide, written from what makers' products chose and why.

How R2R itself is built

17 tools, from its own code, website and Product Hunt page.

Who uses it

No maker's live product on record yet, and 1 open-source projects that declare it in their code.

We haven't found a maker's live product that uses R2R yet — only the open-source projects below, which declare it in their code.

Open source: a project that declares R2R as a dependency in its public code — verifiable, but not necessarily a live product.

Questions makers ask about R2R

What are the alternatives to R2R?

For document parsing, the other options makers' products we track chose most are Reducto (11), Carbon (1), Unstructured (1). Open source or self-hostable among them: Unstructured. Each alternative, with the situation it fits, is on the R2R alternatives page.

Is R2R open source or self-hostable?

Open source, and you can self-host it. source ↗

Can AI coding agents work with R2R?

No llms.txt, official MCP server or CLI found yet.

Who uses R2R?

No maker's live product we track yet; 1 open-source projects declare it in their code. source ↗