🛠️ All DevTools

[DevOps] AI agent that automates infra without hallucinating Bennu is the first zero-hallucination AI agent that automates DevOps and infrastructure workflows using real, pre-approved functions. No fake code, no prompts — just trusted execution. Works offline, runs on any system, and speaks your language (literally).

[Other] Create accessible HTML patterns instantly Generate semantic HTML patterns without the stress. This beginner-friendly tool creates clean, accessible code from simple form inputs. Live preview, instant copy, and follows web standards - perfect for any skill level

[Other] Build smart, tool-using agents in just one line Comprehensive framework for building sophisticated AI agents with multi-LLM support, advanced tool integration, memory systems, and flexible conversation flows.

[Testing] Secure your vibe coded applications Comprehensive end-to-end testing for your vibe coded application. We identify vulnerabilities, UX flaws, functionality bugs, and security issues before they impact your users and your business.

[CLI Tool] Show HN: Linux CLI tool to provide mutex locks for long running bash ops Been exploring claude and spec-based coding, I think it turned out fairly successful. It's just a simple unix-style tool that gives you a single command to use in bash scripts to simplify mutex or semaphore locking of execution.

[API/SDK] Open-Source BCI Platform with Mobile SDK for Rapid Neurotech Prototyping

[Other] Show HN: A 'Choose Your Own Adventure' written in Emacs Org Mode I authored and developed an interactive children&#x27;s book about entrepreneurship and money management. The journey started with Twinery, the open-source tool for making interactive fiction, discovered right here on HN. The tool kindled memories of reading CYOA style books when I was a kid, and I thought the format would be awesome for writing a story my kids could follow along, incorporating play money to learn about transactions as they occurred in the story.<p>Twinery is a fantastic tool, and I used it to layout the story map. I really wanted to write the content of the story in Emacs and Org Mode however. Thankfully, Twinery provided the ability to write custom Story Formats that defined how a story was exported. I wrote a Story Format called Twiorg that would export the Twinery file to an Org file and then a Org export backend (ox-twee) to do the reverse. With these tools, I could go back and forth between Emacs and Twinery for authoring the story.<p>The project snowballed and I ended up with the book in digital and physical book formats. The Web Book is created using another Org export backend.<p>Ten Dollar Adventure: <a href="https:&#x2F;&#x2F;tendollaradventure.com" rel="nofollow">https:&#x2F;&#x2F;tendollaradventure.com</a><p>Sample the Web Book (one complete storyline&#x2F;adventure): <a href="https:&#x2F;&#x2F;tendollaradventure.com&#x2F;sample&#x2F;" rel="nofollow">https:&#x2F;&#x2F;tendollaradventure.com&#x2F;sample&#x2F;</a><p>I couldn&#x27;t muster the effort to write a special org export backend for the physical books unfortunately and used a commercial editor to format these.<p>Twiorg: <a href="https:&#x2F;&#x2F;github.com&#x2F;danishec&#x2F;twiorg">https:&#x2F;&#x2F;github.com&#x2F;danishec&#x2F;twiorg</a><p>ox-twee: <a href="https:&#x2F;&#x2F;github.com&#x2F;danishec&#x2F;ox-twee">https:&#x2F;&#x2F;github.com&#x2F;danishec&#x2F;ox-twee</a><p>Previous HN post on writing the transaction logic using an LLM in Emacs: <a href="https:&#x2F;&#x2F;blog.tendollaradventure.com&#x2F;automating-story-logic-with-llms&#x2F;" rel="nofollow">https:&#x2F;&#x2F;blog.tendollaradventure.com&#x2F;automating-story-logic-w...</a><p>Twinery 2: &lt;<a href="https:&#x2F;&#x2F;twinery.org&#x2F;" rel="nofollow">https:&#x2F;&#x2F;twinery.org&#x2F;</a>&gt; and discussion on HN: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=32788965">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=32788965</a>

[Other] Metaflow: Build, Manage and Deploy AI/ML Systems

[Other] Mkosi – Build Bespoke OS Images

[Database] 🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.

[Other] Show HN: Display Photos on a World Map I had this idea where you would see realtime photos on a map, right now this is simply using cat pics, not sure where to take it from here but maybe it&#x27;s useful to someone. :)<p>GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;stagas&#x2F;worldsnap">https:&#x2F;&#x2F;github.com&#x2F;stagas&#x2F;worldsnap</a>

[DevOps] Show HN: GitGuard - Painless GitHub PR Automations Hey HN,<p>Every team I&#x27;ve been on has cobbled together some sort of combination of GitHub branch protections and custom scripts to make sure that PRs conform to organization policies and best practices.<p>Things like:<p>- When {X} file is changed, require review from team {Y}<p>- When a new db migration is added, ensure that a special set of tests pass<p>- Require multiple approvals when the PR is very large<p>- Add a special label to PRs that include breaking changes<p>- Allow emergencies &#x2F; hotfixes to break glass and bypass all of the above<p>Most teams tend to start out with a little script running in GitHub actions to enforce all of these policies but it tends to get out of hand and become hard to maintain. PRs that should require scrutiny slip through the cracks, and others that should be allowed through are unnecessarily blocked.<p>That&#x27;s why I made GitGuard (<a href="https:&#x2F;&#x2F;gitguard.dev&#x2F;" rel="nofollow">https:&#x2F;&#x2F;gitguard.dev&#x2F;</a>)<p>GitGuard lets you write and maintain these policies in a custom DSL so simple it looks like pseudocode. The policies are checked on every single PR nearly instantly (no need to wait for a GitHub actions runner) and the results are reported in plain english.<p>Right now policies can make simple assertions about PR metadata and take some stateful actions (adding labels, requesting review) but I&#x27;d love to hear more from HN about how GitGuard could be even more useful.

[Build/Deploy] Mill: A better build tool for Java, Scala, and Kotlin

[CLI Tool] Show HN: ggc – A terminal-based Git CLI written in Go Hi HN,<p>I built ggc (<a href="https:&#x2F;&#x2F;github.com&#x2F;bmf-san&#x2F;ggc">https:&#x2F;&#x2F;github.com&#x2F;bmf-san&#x2F;ggc</a>), a terminal-based Git CLI tool written in Go.<p>ggc provides: - A fast interactive UI (like `fzf`) for common Git operations<p>- Traditional subcommands (e.g. `ggc add`, `ggc commit`)<p>- Git-compatible config support (`ggc config` reads from `git config`)<p>- Built-in aliases and workflow automation (e.g. `ggc addcommitpush`)<p>The goal is to improve developer productivity by combining interactive workflows with scriptable CLI operations.<p>It&#x27;s still under active development, but I&#x27;d love feedback from the community!<p>GitHub: <a href="https:&#x2F;&#x2F;github.com&#x2F;bmf-san&#x2F;ggc">https:&#x2F;&#x2F;github.com&#x2F;bmf-san&#x2F;ggc</a> Demo GIF: <a href="https:&#x2F;&#x2F;github.com&#x2F;bmf-san&#x2F;ggc#demo">https:&#x2F;&#x2F;github.com&#x2F;bmf-san&#x2F;ggc#demo</a><p>Thanks!

[Other] Show HN: Improving RAG with chess Elo scores Hello HN,<p>I&#x27;m Ghita, co-founder of ZeroEntropy (YC W25). We build high accuracy search infrastructure for RAG and AI Agents.<p>We just released two new state-of-the-art rerankers zerank-1, and zerank-1-small. One of them is fully open-source under Apache 2.0.<p>We trained those models using a novel Elo score inspired pipeline which we describe in detail in the blog attached. In a nutshell, here is an outline of the training steps: * Collect soft preferences between pairs of documents using an ensemble of LLMs. * Fit an ELO-style rating system (Bradley-Terry) to turn pairwise comparisons into absolute per-document scores. * Normalize relevance scores across queries using a bias correction step, modeled using cross-query comparisons and solved with MLE.<p>You can try the models either through our API (<a href="https:&#x2F;&#x2F;docs.zeroentropy.dev&#x2F;models">https:&#x2F;&#x2F;docs.zeroentropy.dev&#x2F;models</a>), or via HuggingFace (<a href="https:&#x2F;&#x2F;huggingface.co&#x2F;zeroentropy&#x2F;zerank-1-small" rel="nofollow">https:&#x2F;&#x2F;huggingface.co&#x2F;zeroentropy&#x2F;zerank-1-small</a>).<p>We would love this community&#x27;s feedback on the models, and the training approach. A full technical report is also going to be released soon.<p>Thank you!

[Other] The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

[Code Quality] A command-line tool and Xcode Extension for formatting Swift code

[Other] Build effective agents using Model Context Protocol and simple workflow patterns

[Other] DocsGPT is an open-source genAI tool that helps users get reliable answers from knowledge source, while avoiding hallucinations. It enables private and reliable information retrieval, with tooling and agentic system capability built in.

[CLI Tool] Show HN: DataRamen, a Fast SQL Explorer with Automatic Joins and Data Navigation I built DataRamen, a local-first SQL explorer that helps you get the data you need fast, without writing repetitive queries every time.<p>You run it locally from the CLI (no cloud version yet), connect your databases, and you&#x27;re ready to go. The goal is to let you explore and query data like you would in a spreadsheet: intuitive, fast, and without friction.<p>Key features:<p>- Automatic joins &amp; related data navigation: Right-click any row to instantly see related records in other tables (based on foreign keys or references).<p>- Keyboard-driven UI: Hit N to jump to a table, F to filter, and so on, it’s optimized for speed so you can go from question to insight in seconds (this point is still in progress, I find it confortable, but the goal is to make it even better).<p>- Named tabs with saved queries: Keep multiple tabs open with different queries, useful for comparing or cross-checking data. Tabs are saved, so you can get back to your queries at any time.<p>- Instant edit &amp; insert: One click to edit or add rows, no need to write full queries.<p>- Multi-DB support: Connect several databases and search across all of them.<p>- Search across all columns: Find what you need even if you don&#x27;t know the exact column.<p>If you&#x27;ve ever felt slowed down by writing the same SQL over and over just to explore your data, this might save you a ton of time. I’d love feedback or suggestions, especially from folks who wrangle data often.<p>Find more information on <a href="https:&#x2F;&#x2F;dataramen.xyz" rel="nofollow">https:&#x2F;&#x2F;dataramen.xyz</a><p>PS. don&#x27;t be harsh on the logo, I did my best :)