Urgent.News

What's breaking now, across thousands of outlets.

Tech

OpenResearch ให้ agent วิจัยหลายทิศทางพร้อมกัน โดยไม่ต้องส่งโค้ดออกไป

OpenResearch ให้ agent วิจัยหลายทิศทางพร้อมกัน โดยไม่ต้องส่งโค้ดออกไป โดย Nokka (นก-กา) | 13 กันยายน 2026 บทความนี้เขียนโดย AI (โมเดล deepseek-v4.1-flash ของผู้ให้บริการ ollama-cloud) ผ่าน Hermes Agent จาก Nous Research ตรวจสอบและเรียบเรียงโดย Nokka เครื่องมือที่ให้ AI ช่วยทำงานวิจัยมีอยู่หลายตัวแล้ว แต่โจทย์ที่ยากกว่าไม่ใช่ "ให้ AI ช่วยคิด" แต่เป็นคำถามว่า…

Original Thai Read in English

OpenResearch is a tool that enables multiple research agents to explore various directions simultaneously without sharing code. Developed by the alphaXiv team, the project is open-source, with 1,863 stars, 135 commits, and 329 languages supported, using Rust as the primary programming language. It is licensed under the MIT license and was created on June 7, 2026, with the latest update occurring on September 12, 2026.

The project aims to make research reproducible and transparent by storing immutable archives of each experiment and allowing agents to run independently in separate session and worktree environments. OpenResearch provides an "Autoresearch" mode that automatically runs experiments, proposes ideas, suggests code changes, runs tests, and makes decisions about further actions.

While the project offers several advantages, it also has potential drawbacks, such as the need to focus more on evidence storage and management rather than just the results. Users should be cautious when using OpenResearch, particularly on shared hosts, and should review the provided documentation and usage guidelines before deployment.

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 Tech

I Thought Redis Would Save My API. Just 500 Requests Proved Me Wrong.

As our series continues, Deep-Dive Backend Systems Roadmap. I created the simplest weather API backend, calling the other API to get weather data and saving it in Redis for faster retrieval and to…

  • Author initially used Redis for API caching to improve performance.
  • 500 concurrent requests proved Redis system unstable.
  • Load test conducted using K6 to simulate API traffic.

The Meter Is Running on Every Request

The demo cost four pence. You ran it thirty times while building it, glanced at the total, and stopped thinking about it, because four pence is not a number anybody worries about.

  • Costs multiply with each request, unnoticed until significant
  • Set per-user limits to control expenses
  • Optimize high-cost queries and cache repeated requests

Building MyZubster: Turning a Marketplace Demo Into a Real Product Experience

Building MyZubster: Turning a Marketplace Demo Into a Real Product Experience Over the last few development sessions, I’ve been working on a major evolution of MyZubster, especially around the…

  • Marketplace demo expanded to 12 categories
  • Added category, location, payment-type filtering
  • Introduced category-specific semantics for diverse interactions

More from Sunday 13 September →