Sapphire: Rust based package manager for macOS (Homebrew replacement) (🔥 Score: 155+ in 3 hours)

Link: https://readhacker.news/s/6tdG5
Comments: https://readhacker.news/c/6tdG5

Atuin Desktop: Runbooks That Run (🔥 Score: 151+ in 2 hours)

Link: https://readhacker.news/s/6te5i
Comments: https://readhacker.news/c/6te5i

I should have loved biology too (Score: 151+ in 7 hours)

Link: https://readhacker.news/s/6tdpn
Comments: https://readhacker.news/c/6tdpn

Making a smart bike dumb so it works again (❄️ Score: 151+ in 3 days)

Link: https://readhacker.news/s/6t4eU
Comments: https://readhacker.news/c/6t4eU

Are polynomial features the root of all evil? (2024) (Score: 151+ in 11 hours)

Link: https://readhacker.news/s/6tdpP
Comments: https://readhacker.news/c/6tdpP

How long does it take to create a new habit? (2015) (Score: 151+ in 10 hours)

Link: https://readhacker.news/s/6tdHn
Comments: https://readhacker.news/c/6tdHn

Verus: Verified Rust for low-level systems code (❄️ Score: 150+ in 2 days)

Link: https://readhacker.news/s/6t7Cm
Comments: https://readhacker.news/c/6t7Cm

Show HN: Morphik – Open-source RAG that understands PDF images, runs locally (Score: 151+ in 14 hours)

Link: https://readhacker.news/s/6tdiG
Comments: https://readhacker.news/c/6tdiG

Hey HN, we’re Adi and Arnav. A few months ago, we hit a wall trying to get LLMs to answer questions over research papers and instruction manuals. Everything worked fine, until the answer lived inside an image or diagram embedded in the PDF. Even GPT‑4o flubbed it (we recently tried O3 with the same, and surprisingly it flubbed it too). Naive RAG pipelines just pulled in some text chunks and ignored the rest.
We took an invention disclosure PDF (https://drive.google.com/file/d/1ySzQgbNZkC5dPLtE3pnnVL2rW_9...) containing an IRR‑vs‑frequency graph and asked GPT “From the graph, at what frequency is the IRR maximized?”. We originally tried this on gpt-4o, but while writing this used the new natively multimodal model o4‑mini‑high. After a 30‑second thinking pause, it asked for clarifications, then churned out buggy code, pulled data from the wrong page, and still couldn’t answer the question. We wrote up the full story with screenshots here: https://docs.morphik.ai/blogs/gpt-vs-morphik-multimodal.
We got frustrated enough to try fixing it ourselves.
We built Morphik to do multimodal retrieval over documents like PDFs, where images and diagrams matter as much as the text.
To do this, we use Colpali-style embeddings, which treat each document page as an image and generate multi-vector representations. These embeddings capture layout, typography, and visual context, allowing retrieval to get a whole table or schematic, not just nearby tokens. Along with vector search, this could now retrieve exact pages with relevant diagrams and pass them as images to the LLM to get relevant answers. It’s able to answer the question with an 8B llama 3.1 vision running locally!
Early pharma testers hit our system with queries like "Which EGFR inhibitors at 50 mg showed ≥ 30% tumor reduction?" We correctly returned the right tables and plots, but still hit a bottleneck, we weren’t able to join the dots across multiple reports. So we built a knowledge graph: we tag entities in both text and images, normalize synonyms (Erlotinib → EGFR inhibitor), infer relations (e.g. administered_at, yields_reduction), and stitch everything into a graph. Now a single query could traverse that graph across documents and surface a coherent, cross‑document answer along with the correct pages as images.
To illustrate that, and just for fun, we built a graph of 100 Paul Graham’s essays here: https://pggraph.streamlit.app/ You can search for various nodes, (eg. startup, sam altman, paul graham and see corresponding connections). In our system, we create graphs and store the relevant text chunks along with the entities, so on querying, we can extract the relevant entity, do a search on the graph and pull in the text chunks of all connected nodes, improving cross document queries.
For longer or multi-turn queries, we added persistent KV caching, which stores intermediate key-value states from transformer attention layers. Instead of recomputing attention from scratch every time, we reuse prior layers, speeding up repeated queries and letting us handle much longer context windows.
We’re open‑source under the MIT Expat license: https://github.com/morphik-org/morphik-core
Would love to hear your RAG horror stories, what worked, what didn’t and any feedback on Morphik. We’re here for it.

Solidjs: Simple and performant reactivity for building user interfaces (❄️ Score: 150+ in 3 days)

Link: https://readhacker.news/s/6t46z
Comments: https://readhacker.news/c/6t46z

Native visionOS platform support (🔥 Score: 153+ in 3 hours)

Link: https://readhacker.news/s/6teLX
Comments: https://readhacker.news/c/6teLX

π0.5: A VLA with open-world generalization (Score: 153+ in 14 hours)

Link: https://readhacker.news/s/6tdvR
Comments: https://readhacker.news/c/6tdvR

Open Source Projects Receive Funding to Reclaim the Public Internet (🔥 Score: 156+ in 2 hours)

Link: https://readhacker.news/s/6tf7U
Comments: https://readhacker.news/c/6tf7U

Advanced Python Features (Score: 150+ in 4 hours)

Link: https://readhacker.news/s/6tf7Y
Comments: https://readhacker.news/c/6tf7Y

CSS Hell (Score: 150+ in 13 hours)

Link: https://readhacker.news/s/6teev
Comments: https://readhacker.news/c/6teev

The raccoons who made computer magazine ads great (Score: 151+ in 22 hours)

Link: https://readhacker.news/s/6tcBK
Comments: https://readhacker.news/c/6tcBK

Ping, You've Got Whale: AI detection system alerts ships of whales in their path (Score: 150+ in 18 hours)

Link: https://readhacker.news/s/6tdEm
Comments: https://readhacker.news/c/6tdEm

America's cyber defenses are being dismantled from the inside (🔥 Score: 154+ in 2 hours)

Link: https://readhacker.news/s/6tfpY
Comments: https://readhacker.news/c/6tfpY

Show HN: I open-sourced my AI toy company that runs on ESP32 and OpenAI realtime (Score: 150+ in 23 hours)

Link: https://readhacker.news/s/6tcRB
Comments: https://readhacker.news/c/6tcRB

Hi HN! Last year the project I launched here got a lot of good feedback on creating speech to speech AI on the ESP32. Recently I revamped the whole stack, iterated on that feedback and made our project fully open-source—all of the client, hardware, firmware code.
This Github repo turns an ESP32-S3 into a realtime AI speech companion using the OpenAI Realtime API, Arduino WebSockets, Deno Edge Functions, and a full-stack web interface. You can talk to your own custom AI character, and it responds instantly.
I couldn't find a resource that helped set up a reliable, secure websocket (WSS) AI speech to speech service. While there are several useful Text-To-Speech (TTS) and Speech-To-Text (STT) repos out there, I believe none gets Speech-To-Speech right. OpenAI launched an embedded-repo late last year which sets up WebRTC with ESP-IDF. However, it's not beginner friendly and doesn't have a server side component for business logic.
This repo is an attempt at solving the above pains and creating a great speech to speech experience on Arduino with Secure Websockets using Edge Servers (with Deno/Supabase Edge Functions) for fast global connectivity and low latency.

The Gruen Transfer is consuming the internet (Score: 152+ in 5 hours)

Link: https://readhacker.news/s/6tfg2
Comments: https://readhacker.news/c/6tfg2

Apple and Meta fined millions for breaching EU law (Score: 151+ in 4 hours)

Link: https://readhacker.news/s/6tfpb
Comments: https://readhacker.news/c/6tfpb