HRAG – Hybrid RAG on €116/month of Hetzner, officially benchmarked
Self-hosted hybrid RAG on a €116/month cluster — Postgres, BM25, vectors, a reranker, and a public benchmark score for every claim.
What it does
actual screenshots of the live thing… the 512K-document playground, streamed answers, citations you can open. no mockups — mockups would have been easier. pg_textsearch gives real IDF ranking with Block-Max WAND: 88ms over 2 million chunks, where plain tsquery took 7.5 seconds. Vector and lexical arms fuse with a measured 0.3 vector weight — equal weighting scored worse than turning one arm off. A fourth service reads query and chunk together and reorders the window. Worth +3.9 on the public benchmark… and 16 seconds of latency on 2 vCPUs, which is why it ships as a checkbox and not a default. Both numbers are published. Empty retrieval refuses without calling the model. On the benchmark's…from hrag.app
Does a similar job
all alternatives →- FBFastGraphRAG – Better RAG using good old PageRank2024 · github.com · ▲457
Hey there HN! We’re Antonio, Luca, and Yuhang, and we’re excited to introduce Fast GraphRAG, an open-source RAG approach that leverages knowledge graphs and the 25 years old PageRank for better information retrieval and reasoning. Building a good RAG pipeline these days takes a lot of manual optimizations. Most engineers intuitively start from naive RAG: throw everything in a vector database and hope that semantic search is powerful enough. This can work for use cases where accuracy isn’t too important and hallucinations are tolerable, but it doesn’t work for more difficult queries that…
- RORagas – Open-source library for evaluating RAG pipelines2024 · github.com · ▲121
Ragas is an open-source library for evaluating and testing RAG and other LLM applications. Github: https://docs.ragas.io/en/stable/, docs: https://docs.ragas.io/. Ragas provides you with different sets of metrics and methods like synthetic test data generation to help you evaluate your RAG applications. Ragas started off by scratching our own itch for evaluating our RAG chatbots last year. Problems Ragas can solve - How do you choose the best components for your RAG, such as the retriever, reranker, and LLM? - How do you formulate a test dataset…
- ROR2R – Open-source framework for production-grade RAG2024 · github.com · ▲167
Hello HN, I'm Owen from SciPhi (https://www.sciphi.ai/), a startup working on simplifying˛Retrieval-Augmented Generation (RAG). Today we’re excited to share R2R (https://github.com/SciPhi-AI/R2R), an open-source framework that makes it simpler to develop and deploy production-grade RAG systems. Just a quick reminder: RAG helps Large Language Models (LLMs) use current information and specific knowledge. For example, it allows a programming assistant to use your latest documents to answer questions. The idea is to gather all the relevant information…
- RVR2R V2 – A open source RAG engine with prod features2024 · github.com · ▲251
Hi HN! We're building R2R [https://github.com/SciPhi-AI/R2R], an open source RAG answer engine that is built on top of Postgres+Neo4j. The best way to get started is with the docs - https://r2r-docs.sciphi.ai/introduction. This is a major update from our V1 which we have spent the last 3 months intensely building after getting a ton of great feedback from our first Show HN (https://news.ycombinator.com/item?id=39510874). We changed our focus to building a RAG engine instead of a framework, because this is what developers asked for the most.…
PostgreSQL performance and cost across 23 EC2 instance typesJul 2026 · postgres.saneengineer.com · ▲97Hey! I'm Andrei. I got frustrated by how people tend to build overcomplicated backend systems, being "motivated" by big tech case studies and popular books. So, I started exploring lean architecture, and building my digital garden of ideas, approaches and data that align with this direction. Here I want to present one of the tools – Sizing tool for PostgreSQL. I've benchmarked PostgreSQL on different EC2 instances and disks, with different initial data sets to see performance that these instances can give you. And I've built a tool to visualize this data, which I welcome you to explore. So,…
- RHRAGBuilder – Hyperparameter tuning on various RAG parameters2024 · github.com · ▲17
A RAG has several moving parts: data ingestion, retrieval, re-ranking, generation etc.. Each part comes with numerous options. If we consider a toy example, where you could choose from: 5 different chunking methods, 5 different chunk sizes, 5 different embedding models, 5 different retrievers, 5 different re-rankers/ compressors 5 different prompts 5 different LLMs That’s 78,125 distinct RAG configurations! If you could try evaluating each one in just 5 mins, that’d still take 271 days of non-stop trial-and-error effort! In short, it’s kinda impossible to find your optimal RAG setup…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 11d ago · louisabraham.github.io
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 18d ago · simedw.com