R2R: The first open source agentic retrieval system available via API that autonomously researches your documents, searches and scrapes the web, builds knowledge graphs, and delivers comprehensive, citation-backed answers through simple RESTful endpoints.

Hi Product Hunt! 👋

Owen from SciPhi here, we're excited to be launching R2R and our SciPhi Cloud API today.

Simply put, we built R2R because traditional RAG wasn't cutting it for complex research tasks. It's our open-source, agentic retrieval system designed for multi-step reasoning across your docs and the web, complete with citations. R2R is containerized with a simple REST API, so you can add programatic deep research capabilities to your apps.

SciPhi Cloud is available if you want to avoid the infra headache (free tier available!).

We're here all day to answer questions – technical, practical, or otherwise. What are you building that needs smarter retrieval?

Explore R2R on GitHub or sign up at app.sciphi.ai.

Looking forward to hearing your thoughts.

R2R is incredible! We built retrieval and RAG features with it in days instead of weeks or months. The team is super helpful and supportive, too!

Automating research is such a time-saver! 👍

Love seeing more open-source AI tools that automate deep research. The citation-backed answers and autonomous web scraping could be a huge time-saver for data-heavy workflows. Excited to try it out!

@supa_l Thanks - would love to get your feedback when you do!