Urgent.News

What's breaking now, across thousands of outlets.

AI

DevKit: a one-file calculator library with tested formulas — now with an LLM cost calculator

I kept reaching for a quick calculator and landing on pages crowded with ads, pop-ups, and distractions. So I built the tool I wanted instead: a lean calculator site that gets out of the way. DevKit is a one-file calculator library with 69 tools, all running client-side in your browser. The tools are organised into tabbed pages, so you can find the one you need without scrolling through a long…

A new calculator library called DevKit has emerged, offering a streamlined experience for users seeking quick and distraction-free math tools. With a single-file structure, DevKit provides 69 individual calculators that operate directly within a user's web browser. These tools are neatly categorized into tabbed pages, allowing for easy navigation without the need to scroll through an extensive list.

The latest enhancement to DevKit is the inclusion of an LLM (Language Model) cost calculator. This feature is particularly valuable for developers working with language models, as it allows them to estimate the cost of a request and simulate generation speed through a tokens/second simulator. This calculator serves as a valuable resource when planning an LLM feature, offering a quick sense of both cost and speed before any coding begins.

One of the standout aspects of DevKit is its commitment to accuracy. The library's formulas are thoroughly verified through testing, providing users with confidence in the results generated. This verification process ensures that any changes to the formulas can be quickly identified and addressed, preventing potential errors in calculations.

To maintain the reliability of its results, DevKit incorporates a comprehensive testing system for its formulas. This testing mechanism allows the library's creator to identify and rectify any mistakes that may arise when formulas are updated, ensuring that users can always trust the accuracy of the calculations provided.

For those interested in exploring DevKit, it is available for immediate use at the following link. The creators of DevKit welcome feedback and suggestions from users, inviting them to share their thoughts on what additional calculators would prove most useful. By actively seeking input from its users, DevKit aims to continually evolve and meet the diverse needs of its community.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

From Rules to Reasoning: How AI Evolved into Agents

When I look at how artificial intelligence has developed, I see a journey from computers that could only follow instructions to systems that can understand a goal and take steps toward completing it.

  • AI evolved from rule-based systems to agents capable of understanding goals.
  • Progression built upon foundational ideas and technologies.
  • AI agents now perform tasks with external tools and resources.

SlothSort: A Local AI That Tidies Your Downloads Folder and Never Moves a File Without Asking

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady . What I Built My Downloads folder had files named doc_001.pdf , scan_004.pdf , IMG_8291.jpg , and…

  • SlothSort is an open-source AI tool for organizing computer files.
  • Uses Google's Gemma 3 4B model to analyze file contents.
  • Ensures files are never overwritten, deleted, or moved unintentionally.

My logs never leave the box: logwhisper, a local-AI log explainer in Go

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady What I Built logwhisper is a small Go CLI that reads production log lines and explains them in plain…

  • logwhisper is a Go CLI that explains production logs in plain English
  • AI runs locally using open-weight Llama 3.2 model without API keys
  • Tool reduces incident workload and ensures data privacy

More from Sunday 25 October →