Urgent.News

What's breaking now, across thousands of outlets.

Sunday, 11 October 2026 Reading Room

AI

FriendStudy AI — an open-source AI study companion for students

I built FriendStudy AI — an open-source AI study companion for students 📚 This is my submission for the Hacktoberfest Weekend Challenge: Build for a Friend 🤝 💡 What I Built I built FriendStudy AI, an AI-powered study companion designed to help students study more effectively. Students often switch between multiple tools to understand difficult topics, create study plans, practice questions,…

dev.to ·

FriendStudy AI is an open-source AI study companion designed to assist students in studying more effectively. It consolidates various activities such as understanding difficult topics, creating study plans, practicing questions, and tracking progress into a single workspace. The AI-powered companion helps students organize their learning, practice concepts, and develop consistent study habits.

Key features of FriendStudy AI include:

- Asking AI questions about study topics

- Generating personalized study plans

- Practicing with AI-generated quizzes

- Tracking study progress

- Maintaining study streaks

- Organizing daily study goals

- Keeping learning activities together

The tool was built for students seeking a simple study companion to help with understanding concepts, practicing questions, and staying consistent with their studies. Students often struggle not due to lack of motivation, but because planning, learning, and revision are fragmented across different tools. FriendStudy AI aims to bring these activities together, allowing students to spend more time learning and less time organizing their workflow.

The project utilizes a React and JavaScript frontend, a Python and FastAPI backend, and the Qwen 2.5 3B AI model through Ollama. This open-weight model enables experimentation with AI-powered study assistance without relying on proprietary model APIs. By using open-source AI tools, developers have greater freedom to understand, customize, and adapt the system as it evolves.

Open-source AI and open-weight models provide developers with greater flexibility and control over AI systems. For FriendStudy AI, this approach facilitates local model inference and allows for experimentation with different models and configurations. Open innovation is crucial because students and developers should have the opportunity to build useful tools without being entirely dependent on closed platforms.

Upcoming improvements include adding more personalized learning plans, better quiz generation, topic-wise progress tracking, additional study resources, improved mobile responsiveness, and gathering feedback from other developers to enhance the tool further.

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

MCP vs A2A vs ACP: Open Protocols for Multi-Agent Systems, Compared

MCP vs A2A vs ACP: Open Protocols for Multi-Agent Systems, Compared If you're building a multi-agent system, you've hit this question: how should agents talk to tools, and how should they talk to each…

  • Multi-agent systems require open protocols to streamline agent-tool and agent-agent communication.
  • MCP maintains by Anthropic, standardized open protocol; A2A maintained by Google, industry support.
  • MCP solves Agent ↔ Tool/Data layer, A2A solves Agent ↔ Agent layer.

·dev.to

TouchGrass AI: Building a Local AI Companion That Gets You Outside 🌿

TouchGrass AI: Building a Local AI Companion That Gets You Outside 🌿 An AI companion designed to help you spend less time on screens and more time in the real world. 1.

  • TouchGrass AI aims to encourage outdoor activities over screen time
  • App generates personalized outdoor micro-adventures based on user input
  • Local AI implementation prioritizes privacy and offline functionality

·dev.to

A Photographer’s Perspective on New Tools

** The Evolving Lens ** For over a decade, my work as a photographer has centered on observing reality. Capturing genuine human emotion requires patience, natural light, and an eye for unscripted…

  • Photographer sees reality as career focus for over a decade.
  • AI tools enhance, don't replace, creative intent in photography.
  • Technology provides new lens, preserves human perspective in images.

·dev.to

💸 What Does One Amazon Bedrock Prompt Cost? Find Out From the CLI (Hands-on)

🎤 The interview question "Your team wants to add an Amazon Bedrock chatbot. How would you work out what one prompt costs?" It shows up in AIF-C01 prep and in real interviews.

  • Use AWS CLI to send prompt to Bedrock
  • Analyze response for token usage (inputTokens, outputTokens)
  • Calculate cost based on tokens and pricing per 1,000 tokens

·dev.to

DeadZone Drill: offline flashcards that only work when you walk away from the internet

The pitch in one sentence DeadZone Drill turns your study notes into a spoken flashcard drill you run on a walk , with a local open-weight model writing and grading the cards — no account, no API key…

  • DeadZone Drill converts study notes into spoken flashcards.
  • Runs offline using local Gemma 3 model via Ollama.
  • Emphasizes open-source principles with no internet required.

·dev.to

AI and Korean studies

There will be a conference at the Korean Studies Institute in Andong later this month examining the future of Korean studies. I’ve always been uncomfortable with “future” studies — how can we know?

·koreatimes.co.kr

More from Sunday 11 October →