Show HN: Gova – The declarative GUI framework for Go

Hi HN, I’m Matt Mahowald, and together with my cofounder John, we’re launching the public beta of Ragnerock today.As a data scientist, you spend the majority of your time wrangling data. Even though you might have a set of techniques and tricks you like to use, how exactly you treat a particular source of data tends to be fairly bespoke, so you end up writing custom logic each time.Ragnerock was born from the observation that modern LLMs can be used to automate a lot of the grunt work involved in this process, while still allowing for fully customizable pipelines. What’s more, by leveraging techniques like constrained decoding, it’s possible to provide a unified query interface regardless of the data source - bridging raw data sources like text and images with your existing structured data living in your databases.Ragnerock has four main components:- A workflow designer that lets you build LLM-driven data processing and analysis pipelines- A job orchestration layer that runs those workflows- A query interface which lets you inspect the results of those workflows with plain SQL- A notebook system which is 100% API-compatible with Jupyter and runs on your existing kernels, so you can easily pull data into your existing environments and analysesRagnerock also supports bring-your-own AI (OpenAI, Anthropic, and Google APIs), databases, and blob storage, so you can join with your existing datasets and have all outputs flow to your data lake. We’re particularly excited about our web crawling feature, which allows you to scrape websites and trigger workflows on updates: for example, you might point Ragnerock at your favorite blog and run a workflow to assess posts for topics and sentiment.You can try it out at <a href="https:&#x2F;&#x2F;www.ragnerock.com" rel="nofollow">https:&#x2F;&#x2F;www.ragnerock.com</a> ; no credit card needed and the first 20 hours of compute are free. It’s an early-stage product so we’re especially interested in feedback.Happy to answer any questions - John and I will be around in the comments today.

Show HN: Ragnerock, an AI data analysis tool

Show HN: Decaf – rewrites webpage comments using on-device Gemini Nano

Hey HN,We got tired of browser frameworks restricting the LLM, so we removed the framework and gave the LLM maximum freedom to do whatever it&#x27;s trained on. We gave the harness the ability to self correct and add new tools if the LLM wants (is pre-trained on) that.Our Browser Use library is tens of thousands of lines of deterministic heuristics wrapping Chrome (CDP websocket). Element extractors, click helpers, target managemenet (SUPER painful), watchdogs (crash handling, file downloads, alerts), cross origin iframes (if you want to click on an element you have to switch the target first, very anoying), etc.Watchdogs specifically are extremely painful but required. If Chrome triggers for example a native file popup the agent is just completely stuck. So the two solutions are to:
1. code those heuristics and edge cases away 1 by 1 and prevent them
2. give LLM a tool to handle the edge caseAs you can imagine - there are crazy amounts of heuristics like this so you eventually end up with A LOT of tools if you try to go for #2. So you have to make compromises and just code those heuristics away.BUT if the LLM just &quot;knows&quot; CDP well enough to switch the targets when it encounters a cross origin iframe, dismiss the alert when it appears, write its own click helpers, or upload function, you suddenly don&#x27;t have to worry about any of those edge cases.Turns out LLMs know CDP pretty well these days. So we bitter pilled the harness. The concepts that should survive are:
- something that holds and keeps CDP websocket alive (deamon)
- extremely basic tools (helpers.py)
- skill.md that explains how to use itThe new paradigm? SKILL.md + a few python helpers that need to have the ability to change on the fly.One cool example:
We forgot to implement upload_file function. Then mid-task the agent wants to upload a file so it grepped helpers.py, saw nothing, wrote the function itself using raw DOM.setFileInputFiles (which we only noticed that later in a git diff). This was a relly magical moment of how powerful LLMs have become.Compared to other approaches (Playwright MCP, browser use CLI, agent-browser, chrome devtools MCP): all of them wrap Chrome in a set of predefined functions for the LLM. The worst failure mode is silent. The LLM&#x27;s click() returns fine so the LLM thinks it clicked, but on this particular site nothing actually happened. It moves on with a broken model of the world. Browser Harness gives the LLM maximum freedom and perfect context for HOW the tools actually work.Here are a few crazy examples of what browser harness can do:
- plays stockfish <a href="https:&#x2F;&#x2F;x.com&#x2F;shawn_pana&#x2F;status&#x2F;2046457374467379347" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;shawn_pana&#x2F;status&#x2F;2046457374467379347</a>
- sets a world record in tetris <a href="https:&#x2F;&#x2F;x.com&#x2F;shawn_pana&#x2F;status&#x2F;2047120626994012442" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;shawn_pana&#x2F;status&#x2F;2047120626994012442</a>
- figures out how to draw a heart with js <a href="https:&#x2F;&#x2F;x.com&#x2F;mamagnus00&#x2F;status&#x2F;2046486159992480198?s=20" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;mamagnus00&#x2F;status&#x2F;2046486159992480198?s=20</a>You can super easily install it by telling claude code:
`Set up <a href="https:&#x2F;&#x2F;github.com&#x2F;browser-use&#x2F;browser-harness" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;browser-use&#x2F;browser-harness</a> for me.`Repo: <a href="https:&#x2F;&#x2F;github.com&#x2F;browser-use&#x2F;browser-harness" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;browser-use&#x2F;browser-harness</a>What would you call this new paradigm? A dialect?

Show HN: Browser Harness – Gives LLM freedom to complete any browser task

ohai!I&#x27;ve released Lightwhale 3, which is possibly the easiest way to self-host Docker containers.It&#x27;s a free, immutable Linux system purpose-built to live-boot straight into a working Docker Engine, thereby shortcutting the need for installation, configuration, and maintenance. Its simple design makes it easy to learn, and its low memory footprint should make it especially attractive during these times of RAMageddon.If this has piqued your interest, do check it out, along with its easy-to-follow Getting Started guide.In any event,
have a nice day! =)

Show HN: I've built a nice home server OS

I put this together (with Claude) as a semi-gamified way for folks to learn about startup equity. Take a look, and share your scorecard :)

Show HN: Startup Equity Adventure Game

Show HN: SyncVibe – Code with friends in the terminal, each with your own AI

Show HN: VoiceGoat – A vulnerable voice agent for practicing LLM attacks

Show HN: How much of the Linux kernel is written by AI?

I shipped a wiki layer for AI agents that uses markdown + git as the source of truth, with a bleve (BM25) + SQLite index on top. No vector or graph db yet.It runs locally in ~&#x2F;.wuphf&#x2F;wiki&#x2F; and you can git clone it out if you want to take your knowledge with you.The shape is the one Karpathy has been circling for a while: an LLM-native knowledge substrate that agents both read from and write into, so context compounds across sessions rather than getting re-pasted every morning. Most implementations of that idea land on Postgres, pgvector, Neo4j, Kafka, and a dashboard.I wanted to go back to the basics and see how far markdown + git could go before I added anything heavier.What it does:
-&gt; Each agent gets a private notebook at agents&#x2F;{slug}&#x2F;notebook&#x2F;.md, plus access to a shared team wiki at team&#x2F;.-&gt; Draft-to-wiki promotion flow. Notebook entries are reviewed (agent or human) and promoted to the canonical wiki with a back-link. A small state machine drives expiry and auto-archive.-&gt; Per-entity fact log: append-only JSONL at team&#x2F;entities&#x2F;{kind}-{slug}.facts.jsonl. A synthesis worker rebuilds the entity brief every N facts. Commits land under a distinct &quot;Pam the Archivist&quot; git identity so provenance is visible in git log.-&gt; [[Wikilinks]] with broken-link detection rendered in red.-&gt; Daily lint cron for contradictions, stale entries, and broken wikilinks.-&gt; &#x2F;lookup slash command plus an MCP tool for cited retrieval. A heuristic classifier routes short lookups to BM25 and narrative queries to a cited-answer loop.Substrate choices:
Markdown for durability. The wiki outlives the runtime, and a user can walk away with every byte. Bleve for BM25. SQLite for structured metadata (facts, entities, edges, redirects, and supersedes). No vectors yet. The current benchmark (500 artifacts, 50 queries) clears 85% recall@20 on BM25 alone, which is the internal ship gate. sqlite-vec is the pre-committed fallback if a query class drops below that.Canonical IDs are first-class. Fact IDs are deterministic and include sentence offset. Canonical slugs are assigned once, merged via redirect stubs, and never renamed. A rebuild is logically identical, not byte-identical.Known limits:
-&gt; Recall tuning is ongoing. 85% on the benchmark is not a universal guarantee.-&gt; Synthesis quality is bounded by agent observation quality. Garbage facts in, garbage briefs out. The lint pass helps. It is not a judgment engine.-&gt; Single-office scope today. No cross-office federation.Demo. 5-minute terminal walkthrough that records five facts, fires synthesis, shells out to the user&#x27;s LLM CLI, and commits the result under Pam&#x27;s identity: <a href="https:&#x2F;&#x2F;asciinema.org&#x2F;a&#x2F;vUvjJsB5vtUQQ4Eb" rel="nofollow">https:&#x2F;&#x2F;asciinema.org&#x2F;a&#x2F;vUvjJsB5vtUQQ4Eb</a>Script lives at .&#x2F;scripts&#x2F;demo-entity-synthesis.sh.Context. The wiki ships as part of WUPHF, an open source collaborative office for AI agents like Claude Code, Codex, OpenClaw, and local LLMs via OpenCode. MIT, self-hosted, bring-your-own keys. You do not have to use the full office to use the wiki layer. If you already have an agent setup, point WUPHF at it and the wiki attaches.Source: <a href="https:&#x2F;&#x2F;github.com&#x2F;nex-crm&#x2F;wuphf" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;nex-crm&#x2F;wuphf</a>Install: npx wuphf@latestHappy to go deep on the substrate tradeoffs, the promotion-flow state machine, the BM25-first retrieval bet, or the canonical-ID stability rules. Also happy to take &quot;why not an Obsidian vault with a plugin&quot; as a fair question.

Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)

Show HN: AgentSwarms – free hands-on playground to learn agentic AI, no setup required!

Show HN: AgentSwarms – free hands-on playground to learn agentic AI, no setup

Howdy HN! My recent dive into home ownership has brought me a whole new world to navigate w.r.t contractors, insurance claims, etc. I&#x27;ve been leaning heavily on the Dangerous Professional concept for clearer communication. It fits very cleanly as a plugin and has been very high-ROI for me.This is a community implementation. No affiliation with patio11, just a fan of his work.Repo: <a href="https:&#x2F;&#x2F;github.com&#x2F;Tetra-Research&#x2F;dangerous-professional-plugin" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;Tetra-Research&#x2F;dangerous-professional-plu...</a>Install: `npx skills add Tetra-Research&#x2F;dangerous-professional-plugin`

Show HN: Implementing Patio11's "Dangerous Professional" as a Claude Code Plugin

Show HN: I remade my blog into a Windows 3.1 environment

Show HN: Kloak, A secret manager that keeps K8s workload away from secrets

Hey HN, JSS(JumpstartSignal) is a free, ESG-filtered daily stock screener. I built it after some really badly-timed quantum computing stock buys, so I felt I needed to learn more about systematic, longer-horizon approaches and the underlying technicals instead of chasing themes. Three things about it that might be of interest:1. Methodology is fully documented at <a href="https:&#x2F;&#x2F;jumpstartsignal.com&#x2F;how-it-works&#x2F;" rel="nofollow">https:&#x2F;&#x2F;jumpstartsignal.com&#x2F;how-it-works&#x2F;</a> 5-stage pipeline, 54 signals tested individually plus 1,836 combinations evaluated, walk-forward validation across 25 hold periods. Nothing hand-tuned to a single backtest window.2. Many wins, misses, and losses are published as case studies e.g. <a href="https:&#x2F;&#x2F;jumpstartsignal.com&#x2F;case-studies&#x2F;nvda&#x2F;" rel="nofollow">https:&#x2F;&#x2F;jumpstartsignal.com&#x2F;case-studies&#x2F;nvda&#x2F;</a> walks through the 32 times the system flagged NVDA starting at $5.44 in 2018. <a href="https:&#x2F;&#x2F;jumpstartsignal.com&#x2F;case-studies&#x2F;sedg&#x2F;" rel="nofollow">https:&#x2F;&#x2F;jumpstartsignal.com&#x2F;case-studies&#x2F;sedg&#x2F;</a> shows a -49% loss, and <a href="https:&#x2F;&#x2F;jumpstartsignal.com&#x2F;case-studies&#x2F;tsla&#x2F;" rel="nofollow">https:&#x2F;&#x2F;jumpstartsignal.com&#x2F;case-studies&#x2F;tsla&#x2F;</a> explains why the system never flagged Tesla (it passed Stages 1 and 2 on 207 days but only peaked at 20&#x2F;100 in scoring vs the 70 needed for OPPORTUNITY tier). <a href="https:&#x2F;&#x2F;jumpstartsignal.com&#x2F;results&#x2F;" rel="nofollow">https:&#x2F;&#x2F;jumpstartsignal.com&#x2F;results&#x2F;</a> also shows the 10 best entries alongside the 10 worst.3. A genetic algorithm picked the signal weights, but constrained to maintain alpha across multiple market regimes (otherwise it overfits to a single bull market). The constraint dropped some &quot;best in backtest&quot; configurations that only worked 2018-2021.Topline: 2012-2025 backtest at SPOTLIGHT + OPPORTUNITY tier produced +163% alpha vs SPY (results page has the per-trade breakdown).Daily watchlist emailed free; reports + results + case studies are publicly browsable without signup.Happy to take questions about methodology, what the system gets wrong, or why specific tickers landed where they did.

Show HN: A free ESG stock screener that publishes its losses and methodology

Show HN: Blotter, a live map of LAPD radio activity

Forkle (forkle.co.uk) is a daily word game where two thematically linked crosswords occupy the same grid simultaneously. Every tile contains two letters - one belonging to each puzzle - displayed as a diagonal colour split. Where the two puzzles intersect, some tiles share the same letter, giving you a foothold into both crosswords at once.The mechanic has two layers: the shared grid, and the connected themes. Each day&#x27;s two crosswords are thematically paired around a central idea. For example, a previous puzzle was &quot;Same House, Different Kingdoms&quot; - same home, same humans, entirely different worlds. One crossword is the dog&#x27;s world, the other is the cat&#x27;s. The themes are chosen to be related but distinct, which creates an extra layer of satisfaction when the connection clicks.The constraint of forcing two crosswords into one physical space turns out to create genuinely interesting solving decisions - sometimes the two puzzles help each other, sometimes they fight.Built solo over a few months using React, Python, Supabase, Fly.io and Resend. Three months of daily puzzles pre-loaded. Launched two weeks ago.Would love feedback from anyone willing to try it.

Show HN: I built a dual crossword puzzle where two crosswords share one grid

Hey there! I am Luca, I write <a href="https:&#x2F;&#x2F;refactoring.fm&#x2F;" rel="nofollow">https:&#x2F;&#x2F;refactoring.fm&#x2F;</a> and I built Tolaria for myself to manage my own knowledge base (10K notes, 300+ articles written in over 6 years of newslettering) and work well with AI.Tolaria is offline-first, file-based, has first-class support for git, and has strong opinions about how you should organize notes (types, relationships, etc).Let me know your thoughts!

Show HN: Tolaria – Open-source macOS app to manage Markdown knowledge bases

Show HN: Excalidraw but for 3D Drawing

Most RAG setups fail because they treat memory like a static filing cabinet. When every transient bug fix or abandoned rule is stored forever, the context window eventually chokes on noise, spiking token costs and degrading the agent&#x27;s reasoning.This implementation experiments with a biological approach by using the Ebbinghaus forgetting curve to manage context as a living substrate. Memories are assigned a &quot;strength&quot; score where each recall reinforces the data and flattens its decay curve (spaced repetition), while unused data eventually hits a threshold and is pruned.To solve the &quot;logical neighbor&quot; problem where semantic search misses relevant but non-similar nodes, a graph layer is layered over the vector store. Benchmarked against the LoCoMo dataset, this reached 52% Recall@5, nearly double the accuracy of stateless vector stores, while cutting token waste by roughly 84%.Built as a local first MCP server using DuckDB, the hypothesis is that for agents handling long-running projects, &quot;what to forget&quot; is just as critical as &quot;what to remember.&quot; I&#x27;d be interested to hear if others are exploring non-linear decay or similar biological constraints for context management.GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;sachitrafa&#x2F;cognitive-ai-memory" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;sachitrafa&#x2F;cognitive-ai-memory</a>

Show HN: AI memory with biological decay (52% recall)

Show HN: BeVisible.app - Blog that runs itself

This solves no real problem — Element works, there&#x27;s already a Matrix-to-IRC bridge running on half the FOSS networks, and probably nobody under 30 has opened irssi voluntarily this decade.I wrote it anyway because I miss Esc 4 and clunky window-split commands.Matrirc is a local IRC server that speaks Matrix on the back. Point irssi at localhost:6667, log in with Matrix creds, rooms show up as channels.brew tap pawelb0&#x2F;tap
brew install matrirc

Show HN: Matrirc – run irssi in 2026, talk to people on Matrix

Show HN: Gate – AI workers handle dev tickets in a visual workspace

Show HN: Nat-zero – Scale-to-zero NAT instances for AWS (Terraform module)

I used to run a flash games website (SWF files) years ago. I&#x27;ve made a few games of my own. I&#x27;m also an avid gamer and love to play games of all kinds.I&#x27;m also a software engineer, and a few days ago I decided I wanted to run a games website again. So I bought the domain gamevibe.us and with the help of Claude I&#x27;ve been vibe-coding one video game every day since.Happy to answer questions, take feedback, etc

Show HN: Vibe-coding video games with Claude (Day 14: Tetris)

Greetings HN! I&#x27;ve forked the excellent work done by [vlaci&#x2F;git-agecrypt](<a href="https:&#x2F;&#x2F;github.com&#x2F;vlaci&#x2F;git-agecrypt" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;vlaci&#x2F;git-agecrypt</a>), looks like the original project has not been maintained for a while, so I decided to pick it up, update all the dependencies and add some thorough testing.I like the ability to store sensitive data in public repositories, it&#x27;s especially useful when bootstrapping new IaC repositories, you don&#x27;t have anything at the beginning of a new project so there is no place yet to store secrets, this is &quot;a way&quot; of doing it.I know you can use tools like SOPS but I think the transparent approach offered by tools like this one or git-crypt really shine for many use cases.Looking forward to hear your feedback!

Show HN: Git-agecrypt – transparent file-level encryption for Git

I built this for 2 usecases:- When listening to music, I very often what is currently being played. Be it a the current chord, a short lick, etc.
- When transcribing, I don&#x27;t like the workflow of extracting a complete audio and transforming it midi, so I thought having this helper on the side, but still do most of the work by myself could be very useful.Disclaimer: the app is limited by the model&#x27;s performance. Basic-Pitch is a relatively small model which runs super well on consumer laptops. I get around 50FPS of inference on my laptop (AMD Radeon 780M).Of course, this wouldn&#x27;t be possible without:- Tauri: <a href="https:&#x2F;&#x2F;tauri.app&#x2F;" rel="nofollow">https:&#x2F;&#x2F;tauri.app&#x2F;</a>
- Basic Pitch: <a href="https:&#x2F;&#x2F;github.com&#x2F;spotify&#x2F;basic-pitch" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;spotify&#x2F;basic-pitch</a>
- ONNX: <a href="https:&#x2F;&#x2F;onnx.ai&#x2F;" rel="nofollow">https:&#x2F;&#x2F;onnx.ai&#x2F;</a>

Show HN: See your computer's audio output on a real-time piano

Show HN: Auge Vision from Your Terminal

Wouldn&#x27;t be nice to press &lt;C-x C-f&gt; (find-file) and instead of a file path, give it a GitHub URL,  and then just browse the repo in Dired?

Show HN: Browse GitHub repos in Emacs without cloning

Most PDF editors just overlay text boxes. CrabPDF modifies the actual text inside the file. Nothing leaves your computer... no server, no account, works offline.