Urgent.News

What's breaking now, across thousands of outlets.

Saturday, 10 October 2026 Reading Room

AI

TouchGrass: An AI Whose Success Is Measured by How Quickly You Stop Using It 🌱

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built TouchGrass is an AI-powered application built for the Hacktoberfest ’26 Week 1 challenge, Touch Grass . The idea is simple: instead of keeping users glued to a screen, TouchGrass encourages them to step outside and engage with the real world. Users can choose an activity, duration, setting, and…

dev.to ·

TouchGrass is an AI-driven application designed to prompt users to step outside and interact with the physical world, rather than remaining tethered to their devices. Upon launching, users select their preferred activity, duration, location, and level of challenge. The app then generates a customized outdoor task, which the user can complete by enabling Go Outside Mode and turning their phone away.

Later, the user can log their experience, including any photos and personal reflections, in the app's My Submissions section. If the AI model fails to generate a mission, TouchGrass offers fallback activities. The application is built using React and Vite for the frontend, Node.js and Express for the backend, and Hugging Face inference providers for mission generation.

A browser's local storage maintains mission records, reflections, and other data. The codebase is available on GitHub. The project emphasizes the importance of open innovation, as relying on a single proprietary AI model limits flexibility. By using an open-weight model, TouchGrass ensures its mission-generation component remains adaptable.

The ultimate aim of TouchGrass is not to increase screen time but to encourage users to disconnect from technology and appreciate the world around them. The application is deployed on Vercel for the frontend and Render for the backend.

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

Route Once, Fail Over Among Equals: When NOT to Retry an LLM Call

Most LLM APIs I review have one IChatClient and a prayer. Hello goes to the same model as "why does this async code deadlock under load." When that provider returns 503 for twenty minutes, so does the…

  • Only fail over among models of equal quality or reliability.
  • Do not retry when provider returns 400, indicating malformed request.
  • Commit only once when streaming the first token to avoid half-answer.

·dev.to

5 Mistakes That Make LLM Streaming Break on a Flaky Network

Your chat UI looks fine on the office Wi-Fi. Then someone joins from a train, the SSE connection drops mid-sentence, and either the answer restarts from scratch or the model keeps burning tokens while…

  • Tying generation to the HTTP request causes wasted computation when the connection is lost.
  • Lack of sequence IDs prevents clients from reconnecting and resuming the generation process.
  • Using "error" as an event name can confuse the default EventSource error handler.

·dev.to

SAAX Protocol: A Commitment Layer for Agentic Commerce

When an AI agent buys something and the purchase goes wrong, the parties usually discover the same problem: there is no structured record of what was actually committed. The authorization was valid.

  • SAAX Protocol creates vendor-neutral commitment lifecycle for autonomous commerce
  • Handles failed agent attempts with specific status outcomes and merchant storage requirements

·dev.to

Around 1.000 AI products don't appear in corporate access systems

A Reco analysis based on the 2026 State of Agent Security Report examines how AI assistants enter company environments through third-party products.

  • Around 1,000 AI-powered digital assistants may be undetected in company systems
  • Only 282 of 1,280 studied AI products are protected by single sign-on systems
  • Companies urged to verify assistants, limit permissions, and clarify their actions

·dev.to

I built an open-source, self-hosted take on ElevenLabs' Reception.ai

The phone rings at a dental clinic while everyone's hands are busy. Nobody picks up. The caller books somewhere else. Frontdesk.ai is an open-source AI receptionist that picks up instead.

  • Frontdesk.ai is an open-source AI receptionist for phone calls.
  • Inspired by Reception.ai, it's an independent project not affiliated with ElevenLabs.
  • Runs on user's system via Docker Compose with Next.js, Supabase, LiveKit, and more.

·dev.to

More from Saturday 10 October →