🛠️ All DevTools

[Other] Show HN: An Open-Source E-Book Reader for Conversational Reading with an LLM Hi HN! I&#x27;ve been working on BookWith, an open-source e-book reader that integrates AI as your reading companion.<p>The problem: Traditional e-readers are passive. When you encounter something unclear, you have to context-switch to search for it. Your highlights and notes remain isolated, and you can&#x27;t easily connect ideas across different books.<p>My solution: BookWith embeds an AI that maintains full context of what you&#x27;re reading. It features:<p>- Context-aware AI chat: Ask questions about the current page&#x2F;chapter and get instant answers<p>- AI podcast generation: Automatically converts book content into conversational podcasts using Google Cloud TTS<p>- Multi-layer memory system: Short-term (last 5 conversations), mid-term (summarized every 20), and long-term (vector search) memory that maintains continuity across reading sessions<p>- Smart annotations: 5-color highlighting system that AI can reference and analyze<p>Technical stack: Built as a fork of Flow (epub reader), with added LLM integration and vector database for semantic search. Supports multiple LLMs and languages (EN&#x2F;JA&#x2F;ZH).

[IDE/Editor] IntelliJ IDEA & IntelliJ Platform

[Other] Show HN: HMPL – Small Template Language for Rendering UI from Server to Client Hi HN! Together with contributors, we&#x27;ve been making a small template language for a year now, which, in our opinion, can replace HTMX and Alpine.js. It is a mix between EJS and Handlebars, that is, you can make a request with a familiar syntax to the server in HTML right in the markup.<p>Requests are made via fetch and are configured via javascript almost entirely, which is what is needed today to work with the server.<p>The very essence of the template language comes down to minimizing the size of the bundle of the original web application by moving the components to the server and then storing them there. Thus, on the client we get a framework, where we insert components from the server brick by brick.<p>We showed this template language a long time ago, but it was not so mature then, so people had a lot of questions: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=41204552">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=41204552</a><p>Thank you very much to everyone for your attention! Please tell me what you think about the project? It will be interesting to know!

[Other] AI-powered mind mapping that keeps your ideas organized A lightweight 10MB desktop app that supercharges your creativity with AI while keeping your ideas completely private. Organize your mind maps effortlessly with tag-based grouping system for better knowledge management.

[Other] Your AI full-stack developer that never sleeps Stakly: AI-powered development platform for building amazing apps

[Testing] AI-powered Salesforce test cases with integration Chrome extension for Salesforce that automates UI test documentation. It captures real-time user actions and auto-generates structured test cases with video evidence, exporting seamlessly to tools like Azure DevOp saving time and boosting accuracy.

[Other] AI-Powered Hardware Design & Verification Copilot Spec2RTL is an AI copilot that turns natural language hardware specs into Verilog RTL + SystemVerilog testbenches. With self-correction, RAG, and automated validation, it gets you from spec to simulation in minutes. Local (Ollama) + Cloud (Azure) supported.

[DevOps] CNAPP Secure your software supply chain from the first line of code to your production cloud environment. Plexicus is an agentless, open-source-powered platform that simplifies complexity, eliminates blind spots, and puts developers at the center of security.

[API/SDK] Your Bot. Our Number. Go Live in Minutes. Introducing Exotel AgentStream - real-time voice streaming infrastructure for AI voice bots. <20ms latency, 99.95% uptime, telco-grade reliability. Connect bots to users over PSTN, WhatsApp, or WebRTC in minutes. Built for devs, trusted by enterprises.

[Other] OffCrypt Android message encryption PGP style OffCrypt is encryption and messaging application for Android devices that works in a PGP‑style: it uses public‑key cryptography so messages can be encrypted with a recipient’s public key and decrypted only with their private key.

[Other] Instant frontend CRUD from schema — no backend needed. PieCRUD is a Frontend-as-a-Service platform that instantly builds CRUD apps from your schema. Upload your DDL or JSON schema, and get a ready-to-use frontend — perfect for individuals, teachers, internal IT, and small businesses.

[Other] Build and organize tools in a flexible workspace environment Hollow is a plugin-based workspace app where every tool is a card you place, style, and organize freely. It avoids bloat by letting you build only what you need, making it a clean, customizable environment for daily tasks, notes, and creative workflows.

[Build/Deploy] The easiest way to build GitHub workflows OctoLab is a visual tool to design GitHub Actions workflows quickly and intuitively. Use templates, configure jobs and steps with dynamic inputs and export the workflow ready for integration into repository.

[Other] Save & paste your AI prompts without switching tabs Tired of rewriting the same AI prompts or digging through old docs to find them? SuperPrompt is a simple Chrome sidebar that saves your favorite prompts and lets you paste them instantly into any chatbot so you can work faster & Smarter.

[CLI Tool] A free stylized terminal for macOS A Terminal wrapper for macOS. Contribute to nuance-dev/Pinto development by creating an account on GitHub.

[Database] Turn plain language into powerful database queries Turn natural language into SQL and MongoDB queries. Upload your schema, ask questions, and get results with clear explanations — no coding needed. Runs fully in your browser. Private, multilingual, beginner-friendly. Supports multiple databases.

[Other] Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters.<p>This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required!<p>We&#x27;re releasing this to give early users a sense of the latency and voices that will be available in our next release (hopefully next week). We&#x27;d love your feedback! Just FYI, this model is an early checkpoint trained on less than 10% of our total data.<p>We started working on this because existing expressive OSS models require big GPUs to run them on-device and the cloud alternatives are too expensive for high frequency use. We think there&#x27;s a need for frontier open-source models that are tiny enough to run on edge devices!

[Other] Show HN: A benchmark + latency sim for LLM db queries: ClickHouse / Postgres

[Other] Spotting base64 encoded JSON, certificates, and private keys

[Other] Show HN: Tambo – build generative UX web apps