Open-source, cross-platform JavaScript run-time environment that executes JavaScript code outside the browser
We build a Tiny Language Model from scratch in pure Node.js without TensorFlow or PyTorch, implementing neurons, autograd, embeddings, self-attention, FFN, backpropagation, and SFT while observing how individual weights and entire matrices change during training.
This article is not about Puppeteer being a bad tool. Puppeteer is excellent. And competent TLS fingerprinting will bypass most defenses. But there is a class of tasks where even a perfect network stack won't save you — because detection has long since landed at the level of rendering engine behavior. Let's take a look at how Cloudflare and Akamai expose you through WebGL and Canvas, and why “clean” code no longer works.
I share how I built a resume matcher app using tRPC, TypeScript, and Google Vertex AI. The project takes PDF resumes and job postings, extracts text, applies basic NLP for skill detection, and then calls Gemini 1.5 Flash for deeper analysis. Along the way, I explain why tRPC felt faster and cleaner than REST or GraphQL for an MVP, show code snippets from the repo, and discuss both the benefits and trade-offs of this approach.
It’s been a while since I last published anything on Habr, about 10 years or so, and today is the day to share my small open-source project.
The project, called Gaunt Sloth Assistant, is a CLI AI client built with TypeScript (LangChain.js), distributed via npm, and works on Linux, Windows, and Mac. The user is in full control of the prompts, and forming your own system prompt is encouraged, but it has a default one as well.
GitHub: https://github.com/andruhon/gaunt-sloth-assistant
NPM: https://www.npmjs.com/package/gaunt-sloth-assistant
Gaunt Sloth currently has dependencies allowing it to use a simple JSON configuration for VertexAI, Anthropic, Groq, DeepSeek and OpenAI (consequently everyone else who using OpenAI format, e.g. Inception). Hypothetically, it should work with any model supported by LangChain; there’s even a package available for Yandex, which I have never tried, but I think it should work if you install the package and provide a JS config. OLLAMA? It might work; I have never tried, but I will appreciate it if someone shares their experience.
The Gaunt Sloth can review pull requests and match them with requirements from a Jira or GitHub issue, review local diffs, chat, has access to the filesystem, and can write code to the filesystem.
The Gaunt Sloth is a versatile tool with a range of helpful capabilities:
Reviews pull requests (e.g., 42) and matches them with requirements from a Jira or GitHub issue (e.g., 12).
gth pr 42 12
Reviews local diffs.
git --no-pager diff | gth review
Provides an interactive chat session.
gth chat
Has access to the filesystem to read and write code.
gth code
Of course, it has MCP and OAuth, so you can connect to a remote MCP such as Jira and create and edit stories like a boss.
It also has a tiny feature that can log time against a Jira issue when it finishes reviewing a PR. This is not documented yet, but you can find the config example in the release notes or ask me in the comments (as far as I know, Jira MCP can’t do that).
Apart from that, you can supply simple local AI tools in LangChainJS tool format, as simple as this:
import { tool } from "@langchain/core/tools"; import { z } from "zod"; const multiply = tool( ({ a, b }: { a: number; b: number }): number => a * b, {name: "multiply", description: "Multiply two numbers", schema: z.object({ a: z.number(), b: z.number(), })} );
It is very config and guidelines-driven. I have a separate config in each project, setting it up for me and providing the necessary guidelines, so the AI does not screw up because of a lack of information. Also, I have a number of non-coding projects. I have a separate one for Jira with detailed instructions on how to work with it and another for writing.
Automatic data scraping (parsing) has become an essential practice for developers, analysts, and automation specialists. It is used to extract massive amounts of information from websites—from competitors’ prices and reviews to social media content. To achieve this, numerous “scrapers” have been developed—libraries, frameworks, and cloud services that enable programmatic extraction of web data. Some solutions are designed for rapid parsing of static pages, others for bypassing complex JavaScript navigation, and yet others for retrieving data via APIs.
In this article, I will review the top scraping tools—both open source libraries and commercial SaaS/API services—and compare them according to key metrics: • Speed and scalability; • Ability to bypass anti-bot protections; • Proxy support and CAPTCHA recognition; • Quality of documentation; • Availability of APIs and other important features.
Memory leaks in Node.js can be silent killers for your applications. They degrade performance, increase costs, and eventually lead to crashes. Let’s break down common causes and actionable strategies to prevent or fix them.
In today's rapidly advancing technological landscape, natural language processing and comprehension have become essential components of everyday life. Leading the charge in this arena is OpenAI's ChatGPT API, renowned for its exceptional ability to understand and interact with human language. Imagine elevating ChatGPT's functionality to new heights, enabling it to carry out specific tasks based on commands given in natural language. This article aims to shed light on the potential of incorporating function calling into the ChatGPT API, thereby enhancing its utility. I will illustrate through practical examples how such extensions can unlock a myriad of opportunities and applications.
The general trend of technology development is characterized by surges and declines. Consider, for instance, the mass movement of human bodies. Initially, horses and wagons were used, which gradually evolved into a distinct industry. Then trains appeared abruptly. Horses were quickly forgotten, and the focus shifted to a new avenue. Steam became an object of study and evolved into a complex science. Diesel and electricity developed concurrently. At a certain point, steam engines became obsolete, and everyone transitioned to diesel and electricity. Similarly, we are now transitioning to electric cars that require significantly fewer fluids.
Technologies evolve and function until new technologies completely replace them. I believe we are entering an era where framework and Electron technologies may be eclipsed by generative AI. Let's examine some examples.
I develop robots, and I'm often asked, "How to make a robot?" and "Where do you find information and what resources do you use?"
If you don't know where to start and want to create your own robot, this article is for you. In it, I will try to explain the process and also share the first steps you should take.
Microfrontend as it supposed to be: Single Page Application, Server-side rendering and Independent deployments.
Example that proves it's possible using React 18 + Suspense on server and Webpack Module Federation
In this article, we will briefly review a technology that underlies ChatGPT — embeddings. Also we’ll write a simple intelligent search in a codebase of a project.
With the help of the ESLint and Prettier features, you can automate the formatting of your code, make it more expressive and accurate, correspond to specific rules, and avoid errors and bottlenecks even before uploading the code to the shared source storage...
As a side hustle, I teach tech recruiters web and software development technologies using plain English. It helps them with understanding job specs and resumes and it makes all of us, tech people, happier.
I run a weekly newsletter and often get feedback from recruiters via email or LinkedIn DMs.
I thought that I could try to collect feedback using the “Reactions” feature just like LinkedIn or Facebook does. It’s not as informative as personalised messages but is a simple feature that may incentivize more people to provide some general feedback.
Either way, it’s worth trying and as a software developer, I can’t wait to implement it.
This tutorial is about implementing a feature that will be used in real life on my project.
With ML projects still on the rise we are yet to see integrated solutions in almost every device around us. The need for processing power, memory and experimentation has led to machine learning and DL frameworks targeting desktop computers first. However once trained, a model may be executed in a more constrained environment on a smartphone or on an IoT device. A particularly interesting environment to run the model on is browser. Browser-based solutions may be used on a wide range of devices, desktop and mobile, online and offline. The topic of this post is how to prepare a model for the in-browser usage.
This post presents an end-to-end implementations of a model creation in Python and Node.js. The end goal is to create a model and to use it in a browser. I'll use TensorFlow and TensorFlow.js as main frameworks. One could train a model in Python and convert it to JS. Alternative is to train a model directly in javascript, hence omitting the conversion step.
I have more experience in Python and use it in my everyday work. I occasionally use javascript, but have very little experience in the contemporary front-end development. My hope from this post that python developers with little JS experience could use it to kick start their JS usage.
Choosing between Node.js and Ruby on Rails, when choosing a development platform, is a core decision. That affects how the project unfolds over time, and how much server resources will be needed. Both languages can support web applications of high complexity, but each has its advantages and disadvantages. Knowledge of these pros and cons will help to choose the best solution for the proposed project. Let's analyze in more detail and tell you about our choice and experience.
