Urgent.News

What's breaking now, across thousands of outlets.

Saturday, 10 October 2026 Reading Room

AI

Building PlantLens AI for the Hacktoberfest "Touch Grass" Challenge

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built I built PlantLens AI , a privacy-focused, AI-powered botanical assistant. Users simply upload a photo of a plant or leaf, and the application provides an instant health assessment, identifies possible diseases or pests, and outlines practical care instructions (watering, sunlight, and origin…

dev.to ·

This submission introduces PlantLens AI, an open-source AI-driven botanical assistant designed with privacy as its core philosophy. Users simply upload a photo of a plant or leaf, and PlantLens AI delivers an immediate assessment of the plant's health, identifies potential diseases or pests, and provides actionable care instructions such as watering, sunlight requirements, and origin data.

The application is built using Next.js, TypeScript, and Tailwind CSS, creating a clean, nature-inspired user interface. The core intelligence is powered by Google's open-weight Gemma Multimodal Vision model, accessed through a server-side API proxy to ensure user credentials remain secure. PlantLens AI prompts users to physically go outside, perform a single, specified outdoor task, and click a "✓ I Did It" button to celebrate their time spent in the real world.

The project is hosted at plantlensai.vercel.app. The code for the application is available at r67251491-coder / PlantLens-Ai.

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

What happens when an AI burns out

I once took someone off a job because they were burning out. They'd been at it for the best part of two days without a proper break, they'd stopped listening, and they were getting things confidently…

  • AI session ran for nearly two days without proper break
  • Session lost information through context compactions
  • Human intervened to guide AI back on correct path

·dev.to

Agent Graph Engineering, Part 0: I Needed This Before It Had a Name

TL;DR Building a chatbot is easy. Building an AI system you can trace, test, and change without fear is not. I spent years shipping LLM features as intent detection plus nested if/else , and no amount…

  • Agent Graph Engineering journey began before concept had formal name
  • Need for sustainable solution over fleeting trend recognized
  • Graphs provide clear flow visualization and testing framework

·dev.to

Move Slow LLM Calls Off the Request Path with BullMQ in Node.js

If an LLM call can take 20 seconds or more, keep it out of your HTTP handler. Put the work on a BullMQ queue backed by Redis, return a job ID right away with a 202 Accepted , and let a separate worker…

  • Move slow LLM calls to a separate queue using BullMQ in Node.js
  • Return immediate response while dedicated worker handles asynchronous processing
  • Improves retry policy, concurrency control, and failure handling

·dev.to

More from Saturday 10 October →