🛠️ All DevTools

747s and Coding Agents

[CLI Tool] Show HN: Claude-File-Recovery, recover files from your ~/.claude sessions Claude Code deleted my research and plan markdown files and informed me: “I accidentally rm -rf&#x27;d real directories in my Obsidian vault through a symlink it didn&#x27;t realize was there: I made a mistake. “<p>Unfortunately the backup of my documentation accidentally hadn’t run for a month. So I built claude-file-recovery, a CLI-tool and TUI that is able to extract your files from your ~&#x2F;.claude session history and thankfully I was able to recover my files. It&#x27;s able to extract any file that Claude Code ever read, edited or wrote. I hope you will never need it, but you can find it on my GitHub and pip. Note: It can recover an earlier version of a file at a certain point in time.<p>pip install claude-file-recovery

Tove Jansson's criticized illustrations of The Hobbit

[Database] RuVector is a High Performance, Real-Time, Self-Learning, Vector Graph Neural Network, and Database built in Rust.

A Chinese official’s use of ChatGPT revealed an intimidation operation

[Other] Show HN: Badge that shows how well your codebase fits in an LLM's context window Small codebases were always a good thing. With coding agents, there&#x27;s now a huge advantage to having a codebase small enough that an agent can hold the full thing in context.<p>Repo Tokens is a GitHub Action that counts your codebase&#x27;s size in tokens (using tiktoken) and updates a badge in your README. The badge color reflects what percentage of an LLM&#x27;s context window the codebase fills: green for under 30%, yellow for 50-70%, red for 70%+. Context window size is configurable and defaults to 200k (size of Claude models).<p>It&#x27;s a composite action. Installs tiktoken, runs ~60 lines of inline Python, takes about 10 seconds. The action updates the README but doesn&#x27;t commit, so your workflow controls the git strategy.<p>The idea is to make token size a visible metric, like bundle size badges for JS libraries. Hopefully a small nudge to keep codebases lean and agent-friendly.<p>GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;qwibitai&#x2F;nanoclaw&#x2F;tree&#x2F;main&#x2F;repo-tokens" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;qwibitai&#x2F;nanoclaw&#x2F;tree&#x2F;main&#x2F;repo-tokens</a>

[Other] Building secure, scalable agent sandbox infrastructure

[Other] We deserve a better streams API for JavaScript

Show HN: RetroTick – Run classic Windows EXEs in the browser RetroTick parses PE&#x2F;NE&#x2F;MZ binaries, emulates an x86 CPU, and stubs enough Win32&#x2F;Win16&#x2F;DOS APIs to run classics like FreeCell, Minesweeper, Solitaire and QBasic, entirely in the browser. Built with Preact + Vite + TypeScript.<p>Demo: <a href="https:&#x2F;&#x2F;retrotick.com" rel="nofollow">https:&#x2F;&#x2F;retrotick.com</a><p>GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;lqs&#x2F;retrotick" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;lqs&#x2F;retrotick</a>

[Other] OpenSandbox is a general-purpose sandbox platform for AI applications, offering multi-language SDKs, unified sandbox APIs, and Docker/Kubernetes runtimes for scenarios like Coding Agents, GUI Agents, Agent Evaluation, AI Code Execution, and RL Training.

[Other] Show usage stats for OpenAI Codex and Claude Code, without having to login.

Making Video Games in 2025 (without an engine)

[Code Quality] Show HN: CodeLeash: framework for quality agent development, NOT an orchestrator Hi HN,<p>I built my first project using an LLM in mid-2024. I&#x27;ve been excited ever since. But of course, at some point it all turns into a mess.<p>You see, software is an intricate interwoven collection of tiny details. Good software gets many details right; and does not regress as it gains functionality.<p>My bootstrapped startup, ApprovIQ (<a href="https:&#x2F;&#x2F;approviq.com" rel="nofollow">https:&#x2F;&#x2F;approviq.com</a>) is trying to break into a mature market with multiple fully featured competitors. I need to get the details right: MVP quality won&#x27;t sell. So I opted for Test-Driven Development, the classic red&#x2F;green&#x2F;refactor. Writing tests that fail - then making them pass - forces you to document in your tests every decision that went into the code. This makes it a universal way to construct software. With TDD, you don&#x27;t need to hold context in your head about how things should work. Your software can work as intricate as you like and still be resilient to regression. Bug in a third-party dependency? Get a failing test, make it pass. Anyone who undoes your fix will see the test fail.<p>At the same time as doing TDD with Claude Code, I also discovered that agents obey <i>all</i> instructions put in front of them! I started to add super-advanced linting: architectural guideline enforcement, scripts that walk the codebase&#x27;s AST and enforce my architecture, I even added one that enforces only our brand colors in our codebase. That one is great because it prevents agents from picking ugly &quot;AI generic&quot; colors in frontends. Because the check blocks commits with ugly colors, our product looks way less like an AI built it - without human involvement.<p>In time I was no longer in the details of what the agent was building and was mostly supervising the TDD process while it implemented our product. Once that got tedious, I automated that into a state machine too.<p>All the ideas that now allow me build at high quality are in this repo.<p>This isn&#x27;t your weekend vibe project. I&#x27;ve spent months refining the framework. There are rough edges but it&#x27;s better out and rough than in hiding until perfect.<p>Hopefully some ideas here help you or your agent. I recommend cloning it and letting your agent have a look! And if you want to contribute please to - and if you want to get in touch, contact details in my profile.<p>Thanks for looking.

[Other] Linux explores new way of authenticating developers and their code

[CLI Tool] Show HN: Unfucked – version every change between commits - local-first I built <i>unf</i> after I pasted a prompt into the wrong agent terminal and it overwrote hours of hand-edits across a handful of files. Git couldn&#x27;t help because I hadn&#x27;t finished&#x2F;committed my in progress work. I wanted something that recorded every save automatically so I could rewind to any point in time. I wanted to make it difficult for an agent to permanently screw anything up, even with an errant <i>rm -rf</i><p><i>unf</i> is a background daemon that watches directories you choose (via CLI) and snapshots every text file on save. It stores file contents in an object store, tracks metadata in SQLite, and gives you a CLI to query and restore any version. The install includes a UI, as well to explore the history through time.<p>The tool skips binaries and respects `.gitignore` if one exists. The interface borrows from git so it should feel familiar: <i>unf log</i>, <i>unf diff</i>, <i>unf restore</i>.<p>I say &quot;UN-EF&quot; vs U.N.F, but that&#x27;s for y&#x27;all to decide: I started by calling the project Unfucked and got unfucked.ai, which if you know me and the messes I get myself into, is a fitting purchase.<p>The CLI command is `unf` and the Tauri desktop app is titled &quot;Unfudged&quot; (kids safe name).<p>How it works: <a href="https:&#x2F;&#x2F;unfucked.ai&#x2F;tech" rel="nofollow">https:&#x2F;&#x2F;unfucked.ai&#x2F;tech</a> (summary below)<p>The daemon uses FSEvents on macOS and inotify on Linux. When a file changes, `unf` hashes the content with BLAKE3 and checks whether that hash already exists in the object store — if it does, it just records a new metadata entry pointing to the existing blob. If not, it writes the blob and records the entry. Each snapshot is a row in SQLite. Restores read the blob back from the object store and overwrite the file, after taking a safety snapshot of the current state first (so restoring is itself reversible).<p>There are two processes. The core daemon does the real work of managing FSEvents&#x2F;inotify subscriptions across multiple watched directories and writing snapshots. A sentinel watchdog supervises it, kept alive and aligned by launchd on macOS and systemd on Linux. If the daemon crashes, the sentinel respawns it and reconciles any drift between what you asked to watch and what&#x27;s actually being watched. It was hard to build the second daemon because it felt like conceding that the core wasn&#x27;t solid enough, but I didn&#x27;t want to ship a tool that demanded perfection to deliver on the product promise, so the sentinel is the safety net.<p>Fingers crossed, I haven’t seen it crash in over a week of personal usage on my Mac. But, I don&#x27;t want to trigger &quot;works for me&quot; trauma.<p>The part I like most: On the UI, I enjoy viewing files through time. You can select a time section and filter your projects on a histogram of activity. That has been invaluable in seeing what the agent was doing.<p>On the CLI, the commands are composable. Everything outputs to stdout so you can pipe it into whatever you want. I use these regularly and AI agents are better with the tool than I am:<p><pre><code> # What did my config look like before we broke it? unf cat nginx.conf --at 1h | nginx -t -c &#x2F;dev&#x2F;stdin # Grep through a deleted file unf cat old-routes.rs --at 2d | grep &quot;pub fn&quot; # Count how many lines changed in the last 10 minutes unf diff --at 10m | grep &#x27;^[+-]&#x27; | wc -l # Feed the last hour of changes to an AI for review unf diff --at 1h | pbcopy # Compare two points in time with your own diff tool diff &lt;(unf cat app.tsx --at 1h) &lt;(unf cat app.tsx --at 5m) # Restore just the .rs files that changed in the last 5 minutes unf diff --at 5m --json | jq -r &#x27;.changes[].file&#x27; | grep &#x27;\.rs$&#x27; | xargs -I{} unf restore {} --at 5m # Watch for changes in real time watch -n5 &#x27;unf diff --at 30s&#x27; </code></pre> What was new for me: I came to Rust in Nov. 2025 honestly because of HN enthusiasm and some FOMO. No regrets. I enjoy the language enough that I&#x27;m now working on custom clippy lints to enforce functional programming practices. This project was also my first Apple-notarized DMG, my first Homebrew tap, and my second Tauri app (first one I&#x27;ve shared).<p>Install &amp; Usage:<p><pre><code> &gt; brew install cyrusradfar&#x2F;unf&#x2F;unfudged </code></pre> Then <i>unf watch</i> in a directory. <i>unf help</i> covers the details (or ask your agent to coach).

[CLI Tool] Cronboard: A terminal-based dashboard for managing cron jobs

RCade: Building a Community Arcade Cabinet

[Other] Show HN: Rev-dep – 20x faster knip.dev alternative build in Go

[Other] Launch HN: Cardboard (YC W26) – Agentic video editor Hey HN - we&#x27;re Saksham and Ishan, and we’re building Cardboard (<a href="https:&#x2F;&#x2F;www.usecardboard.com">https:&#x2F;&#x2F;www.usecardboard.com</a>).<p>It lets you go from raw footage to an edited video by describing what you want in natural language.<p>Try it out at <a href="https:&#x2F;&#x2F;demo.usecardboard.com">https:&#x2F;&#x2F;demo.usecardboard.com</a> (no login required).<p>Also, there’s a demo video at: <a href="https:&#x2F;&#x2F;www.usecardboard.com&#x2F;share&#x2F;fUN2i9ft8B46">https:&#x2F;&#x2F;www.usecardboard.com&#x2F;share&#x2F;fUN2i9ft8B46</a><p>People sit on mountains of raw assets - product walkthroughs, customer interviews, travel videos, screen recordings, changelogs, etc. - that could become testimonials, ads, vlogs, launch videos, etc.<p>Instead they sit in cloud storage &#x2F; hard drives because getting to a first cut takes hours of scrubbing through the raw footage manually, arranging clips in correct sequence, syncing music, exporting, uploading to a cloud storage to share, and then getting feedback on WhatsApp&#x2F;iMessage&#x2F;Slack, then re-doing the same thing again till everyone is happy.<p>We grew up together and have been friends for 15 years. Saksham creates content on socials with ~250K views&#x2F;month and kept hitting the wall where editing took longer than creating. Ishan was producing launch videos for HackerRank&#x27;s all-hands demo days and spent most of his time on cuts and sequencing rather than storytelling. We both felt that while tools like Premiere Pro and DaVinci are powerful, they have a steep learning curve and involve lots of manual labor.<p>So we built Cardboard. You tell it to &quot;make a 60s recap from this raw footage&quot; or &quot;cut this into a 20s ad&quot; or &quot;beat-sync this to the music I just added&quot; and it proposes a first draft on the timeline that you can refine further.<p>We built a custom hardware-accelerated renderer on WebCodecs &#x2F; WebGL2, there’s no server-side rendering, no plugins, everything runs in your browser (client-side). Video understanding tasks go through a series of Cloud VLMs + traditional ML models, and we use third party foundational models for agent orchestration. We also give a dropdown for this to the end user.<p>We&#x27;ve shipped 13 releases since November (<a href="https:&#x2F;&#x2F;www.usecardboard.com&#x2F;changelog">https:&#x2F;&#x2F;www.usecardboard.com&#x2F;changelog</a>). The editor handles multi-track timelines with keyframe animations, shot detection, beat sync via percussion detection, voiceover generation, voice cloning, background removal, multilingual captions that are spatially aware of subjects in frame, and Premiere Pro&#x2F;DaVinci&#x2F;FCP XML exports so you can move projects into your existing tools if you want.<p>Where we&#x27;re headed next: real-time collaboration (video git) to avoid inefficient feedback loops, and eventually a prediction engine that learns your editing patterns and suggests the next low entropy actions - similar to how Cursor&#x27;s tab completion works, but for timeline actions.<p>We believe that video creation tools today are stuck where developer tools were in the early 2000s: local-first, zero collaboration with really slow feedback loops.<p>Here are some videos that we made with Cardboard: - <a href="https:&#x2F;&#x2F;www.usecardboard.com&#x2F;share&#x2F;YYsstWeWE9KI">https:&#x2F;&#x2F;www.usecardboard.com&#x2F;share&#x2F;YYsstWeWE9KI</a> - <a href="https:&#x2F;&#x2F;www.usecardboard.com&#x2F;share&#x2F;nyT9oj93sm1e">https:&#x2F;&#x2F;www.usecardboard.com&#x2F;share&#x2F;nyT9oj93sm1e</a> - <a href="https:&#x2F;&#x2F;www.usecardboard.com&#x2F;share&#x2F;xK9mP2vR7nQ4">https:&#x2F;&#x2F;www.usecardboard.com&#x2F;share&#x2F;xK9mP2vR7nQ4</a><p>We would love to hear your thoughts&#x2F;feedback.<p>We&#x27;ll be in the comments all day :)

Smallest transformer that can add two 10-digit numbers