A visual AI interface to understand papers/books/topics
When I do real research — reading papers, books, or trying to understand a complex topic — it never happens in one sitting. I explore a bit, get interrupted, come back days later, ask new questions, find new sources, and gradually build understanding. Existing AI tools are great at answering questions once, but they reset context every time. Notes tools preserve text, but not understanding — they don’t help me reconnect ideas, revisit sources, or see how my thinking has evolved. I built Kerns to sit in between. Kerns is an AI research workspace designed for research that unfolds over time.…
A visual AI interface to understand papers/books/topics launched on October 3, 2025 with 17 votes, #609 of 8,178 launches that month and more than 90% of that year's launches. The site was still online in September 2026, 1 year on.
In plain words
This AI interface helps users understand papers, books, and topics by providing summaries while maintaining access to original source material. Unlike standard chatbots, it lets users dive into specific sections, easily reference the source text, and control context during research. It's designed for students, researchers, and anyone seeking deeper comprehension of complex documents without losing track of original content.
written from the facts on this page · September 2026
From the sources
Kerns is verifiable research for the buy side. Cowork with AI across public filings and your private corpus — every number cites its source, every reasoning step is on the page, and outputs export to Excel with citations intact.
Kerns produces verifiable research across public filings and your private corpus — refinable line by line. Every number cites its source. Every reasoning step is on the page. Open a Kerns answer. Click a number. The PDF opens to the exact source row, highlighted. There is no “where did this come from” moment, because the answer is always one click away. Drop in your existing model. Kerns reads sheets and cells, writes back when you let it, and cites the cell it used the same way it cites a 10-K page. A memo footnote can point at Model · Q3 Numbers!C5 — click the chip and the workbook opens to that cell, highlighted. A Kerns framework is a reusable analytical recipe — the rubric an analyst…from kerns.ai
In the maker’s words, at launch
I feel like LLMs can help me understand anything. However, after I get a summary, I can't dive in to parts that I find interesting; can't refer to original source easily and can't control context with chatbots. This is an attempt to solve for a complete knowledge consumption experience with AI . Please give me…
Does a similar job
all alternatives →
Open Paper2025 · openpaper.ai · ▲289Hi HN! Open Paper allows you to annotate and understand your research papers with an AI copilot. I wanted a paper-reading assistant that let met actually dig into papers in-place while benefiting from AI tooling. When it comes to studying, I'm not a fan of the typical chat interfaces that obfuscate uploaded files and turn them into black box 'content'. Hence, I've implemented a split-pane view. To mitigate the risk of hallucinations, all AI responses come with grounded citations that refer back to the source material in-flow. Some feature highlights: - Actually read your papers in one place…
Integrations in SpineApr 2026 · integrations.getspine.ai · ▲295AI that synthesize and researches info across multiple apps
Portals2025 · useportals.dev · ▲128I'm building a workspace for doing focus work while also managing constant multi-tasking and context-switching that's required in a lot of roles. Currently this is done by using a notes system where we can split-screen AI chat, an object-based data table system for tracking entities, as well as viewing other documents. We can define agents directly from documents by giving instructions in plain language and then defining the trigger conditions. This helps automate workflows directly in the place where we're reading and writing content. I'm continuing to experiment with instructions and…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, October 2025
the whole month →
I went down the rabbit hole on a side project and ended up building this: Strange Attractors(https://blog.shashanktomar.com/posts/strange-attractors). It’s built with three.js. Working on it reminded me of the little "maths for fun" exercises I used to do while learning programming in early days. Just trying things out, getting fascinated and geeky, and being surprised by the results. I spent way too much time on this, but it was extreme fun. My favorite part: someone pointed me to the Simone Attractor on Threads. It is a 2D attractor and I asked GPT to extrapolate it to…
AI · Oct 2025 · blog.shashanktomar.com
Autism Simulator▲779Hey all, I built this. It’s not trying to capture every autistic experience (that’d be impossible). It’s based on my own lived experience as well as that of friends on the spectrum. I'm trying to give people a feel for what masking, decision fatigue, and burnout can look like day-to-day. That’s hard to explain in words, but easier to show through choices and stats. I'm not trying to "define autism". I’ve gotten good feedback here about resilience, meds, and difficulty tuning. I’ll keep tweaking it. If even a few people walk away thinking, "ah, maybe that’s why my coworker struggles in those…
Life & fun · 2025 · autism-simulator.vercel.app
