🛠️ Hacker News Tools

[CLI Tool] Show HN: I used Claude Code to discover connections between 100 books I think LLMs are overused to summarise and underused to help us read deeper.<p>I built a system for Claude Code to browse 100 non-fiction books and find interesting connections between them.<p>I started out with a pipeline in stages, chaining together LLM calls to build up a context of the library. I was mainly getting back the insight that I was baking into the prompts, and the results weren&#x27;t particularly surprising.<p>On a whim, I gave CC access to my debug CLI tools and found that it wiped the floor with that approach. It gave actually interesting results and required very little orchestration in comparison.<p>One of my favourite trail of excerpts goes from Jobs’ reality distortion field to Theranos’ fake demos, to Thiel on startup cults, to Hoffer on mass movement charlatans (<a href="https:&#x2F;&#x2F;trails.pieterma.es&#x2F;trail&#x2F;useful-lies&#x2F;" rel="nofollow">https:&#x2F;&#x2F;trails.pieterma.es&#x2F;trail&#x2F;useful-lies&#x2F;</a>). A fun tendency is that Claude kept getting distracted by topics of secrecy, conspiracy, and hidden systems - as if the task itself summoned a Foucault’s Pendulum mindset.<p>Details:<p>* The books are picked from HN’s favourites (which I collected before: <a href="https:&#x2F;&#x2F;hnbooks.pieterma.es&#x2F;" rel="nofollow">https:&#x2F;&#x2F;hnbooks.pieterma.es&#x2F;</a>).<p>* Chunks are indexed by topic using Gemini Flash Lite. The whole library cost about £10.<p>* Topics are organised into a tree structure using recursive Leiden partitioning and LLM labels. This gives a high-level sense of the themes.<p>* There are several ways to browse. The most useful are embedding similarity, topic tree siblings, and topics cooccurring within a chunk window.<p>* Everything is stored in SQLite and manipulated using a set of CLI tools.<p>I wrote more about the process here: <a href="https:&#x2F;&#x2F;pieterma.es&#x2F;syntopic-reading-claude&#x2F;" rel="nofollow">https:&#x2F;&#x2F;pieterma.es&#x2F;syntopic-reading-claude&#x2F;</a><p>I’m curious if this way of reading resonates for anyone else - LLM-mediated or not.

[Database] Generate QR Codes with Pure SQL in PostgreSQL

[Other] Show HN: Porting xv6 to HiFive Unmatched board Hi HN,<p>I ported the teaching OS xv6-riscv to HiFive Unmatched and got it running on real hardware, including passing usertests.<p>I&#x27;ve been self-studying OS internals using the MIT 6.1810 materials. After finishing most of the labs, I was eager to see what it&#x27;s like to run the OS on bare metal, rather than QEMU.<p>The Unmatched may not have the latest RISC-V features, but it&#x27;s well-documented, and the Rev B release has made it more affordable, which makes it a good learning platform.<p>The porting process involved several interesting challenges:<p>- Hardware Quirks: Handling things like enabling A&#x2F;D bits in PTEs (the hardware doesn&#x27;t set them automatically, causing page faults), proper handling of interrupts, and instruction cache synchronization.<p>- Boot Flow: xv6 expects M-mode on startup, but standard RISC-V boot flows (typically via OpenSBI) jump to S-mode. To bridge this gap, I created a minimal U-Boot FIT image that contains only the xv6 kernel. This way, U-Boot SPL handles the complex CPU&#x2F;DDR initialization, then hands control to xv6 in M-mode (skipping OpenSBI).<p>- Drivers: Ported an SPI SD card driver, replacing the virtio disk driver.<p>I wrote up implementation notes here: <a href="https:&#x2F;&#x2F;github.com&#x2F;eyengin&#x2F;xv6-riscv-unmatched&#x2F;blob&#x2F;unmatched&#x2F;doc&#x2F;NOTES.md" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;eyengin&#x2F;xv6-riscv-unmatched&#x2F;blob&#x2F;unmatche...</a><p>Hopefully, this is useful for others who are learning OS internals and want to try running their code on real RISC-V hardware.

[Other] Bare metal programming with RISC-V guide (2023)

[Other] Show HN: I vibecoded an ARM64 operating system that boots on real hardware VibeOS is a retro operating system that boots on qemu and Pi Zero 2W. I built this with Claude code in about 4 weeks.

[Other] Fly's Sprites.dev addresses dev environment sandboxes and API sandboxes together

[Other] Show HN: Rocket Launch and Orbit Simulator I (17y&#x2F;o) have been developing a rocket launch simulation that allows the user to explore what it&#x27;s like launching a rocket from earth and putting it into orbit. This idea originally started as an educational simulation but as i&#x27;ve gone more down the rabbit hole the more i&#x27;ve wanted to make it realistic. The problem is that I&#x27;ve never had a formal orbital mechanics class or anything like that so I don&#x27;t know what I&#x27;m missing, what I currently have implemented is:<p><pre><code> Variable gravity Variable Atmospheric drag (US Standard Atmosphere 1976) Multi-stage rockets Closed-loop guidance &#x2F; pitch programs (works well within ranges 350km to 600km) Orbital prediction and thrusting options to change your orbit. </code></pre> The feedback I&#x27;m looking for is: UI improvements and possible future physics implementations that I can work on.<p>Current code and physics can be found at: <a href="https:&#x2F;&#x2F;github.com&#x2F;donutTheJedi&#x2F;Rocket-Launch-Simulation" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;donutTheJedi&#x2F;Rocket-Launch-Simulation</a>

[Other] Show HN: EuConform – Offline-first EU AI Act compliance tool (open source) I built this as a personal open-source project to explore how EU AI Act requirements can be translated into concrete, inspectable technical checks.<p>The core idea is local-first compliance: – risk classification (Articles 5–15, incl. prohibited use cases) – bias evaluation using CrowS-Pairs – automatic Annex IV–oriented PDF reports – no cloud services or external APIs (browser-based + Ollama)<p>I’m especially interested in feedback on whether this kind of technical framing of AI regulation makes sense in real-world projects.

[Other] Show HN: Commit-based code review instead of PR-based Hi HN,<p>I’m experimenting with commit-based code review as an alternative to PR-based review.<p>Instead of analyzing large PR diffs, this reviews each commit incrementally, while context is still fresh. It’s fully configurable and intentionally low-noise, high signal - focused on catching issues that tend to slip through and compound over time.<p>The goal isn’t to replace CI or PR review, but to move some feedback earlier:<p>risky changes hidden in small diffs<p>architectural or consistency drift<p>performance or security footguns<p>Happy to answer questions

[Other] Show HN: A website that auctions itself daily Hi HN, I built this side project earlier this week. It executes an English auction on Solana with a reserve price of 0.1 SOL. Auction winner gets control of a Codex editor. Auction losers get refunded (minus a &lt;$0.01 processing fee). The Codex agent operates in a sandbox and can only output HTML&#x2F;JS&#x2F;CSS.<p>The project is open-source: <a href="https:&#x2F;&#x2F;github.com&#x2F;neelsomani&#x2F;the-daily-auction" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;neelsomani&#x2F;the-daily-auction</a>

[Other] Zirgen: Compiler for a Domain-Specific Language

[Other] Embassy: Modern embedded framework, using Rust and async

[Other] Show HN: Catnip – Run Claude Code from Your iPhone Using GitHub Codespaces Hi HN — I built Catnip, an open-source iOS app that lets you run Claude Code against a real development environment from your phone.<p>Under the hood it spins up a GitHub Codespace, installs Claude Code, and connects the iOS client to it securely. You can use a full terminal when needed, or a lightweight native UI for monitoring and interaction.<p>I built this because Claude Code is most useful when it has access to a persistent environment with plugins, tools, and real repos — and I wanted that flexibility away from my laptop.<p>GitHub gives personal users 120 free Codespaces hours&#x2F;month, and Catnip automatically shuts down inactive instances.<p>Open source: <a href="https:&#x2F;&#x2F;github.com&#x2F;wandb&#x2F;catnip" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;wandb&#x2F;catnip</a> App Store: <a href="https:&#x2F;&#x2F;apps.apple.com&#x2F;us&#x2F;app&#x2F;w-b-catnip&#x2F;id6755161660">https:&#x2F;&#x2F;apps.apple.com&#x2F;us&#x2F;app&#x2F;w-b-catnip&#x2F;id6755161660</a><p>Happy to answer questions or hear feedback.

[CLI Tool] Show HN: Miditui – a terminal app/UI for MIDI composing, mixing, and playback

[API/SDK] Bose has released API docs and opened the API for its EoL SoundTouch speakers

[Other] Show HN: DeepDream for Video with Temporal Consistency I forked a PyTorch DeepDream implementation and added video support with temporal consistency. It produces smooth DeepDream videos with minimal flickering, and is highly flexible including many parameters and supports multiple pretrained image classifiers including GoogLeNet. Check out the repo for sample videos! Features:<p>- Optical flow warps previous hallucinations into the current frame<p>- Occlusion masking prevents ghosting and hallucination transfer when objects move<p>- Advanced parameters (layers, octaves, iterations) still work<p>- Works on GPU, CPU, and Apple Silicon

[Other] ASCII-Driven Development

[Other] Claude Code CLI broken

[Other] Show HN: I visualized the entire history of Citi Bike in the browser Each moving arrow represents one real bike ride out of 291 million, and if you&#x27;ve ever taken a Citi Bike before, you are included in this massive visualization!<p>You can search for your ride using Cmd + K and your Citi Bike receipt, which should give you the time of your ride and start&#x2F;end station.<p>Everything is open source: <a href="https:&#x2F;&#x2F;github.com&#x2F;freemanjiang&#x2F;bikemap" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;freemanjiang&#x2F;bikemap</a><p>Some technical details: - No backend! Processed data is stored in parquet files on a Cloudflare CDN, and queried directly by DuckDB WASM<p>- deck.gl w&#x2F; Mapbox for GPU-accelerated rendering of thousands of concurrent animated bikes<p>- Web Workers decode polyline routes and do as much precomputation as possible off the main thread<p>- Since only (start, end) station pairs are provided, routes are generated by querying OSRM for the shortest path between all 2,400+ station pairs

[Other] Show HN: Seapie – a Python debugger where breakpoints drop into a REPL