← Discover
GitHub · alphaXiv/OpenResearch↑ +120 today

AI workspace that accelerates research processes

AlphaXiv is a framework that allows you to run parallel research agents using different AI models. Developed in Rust, this open-source tool aims to accelerate data collection processes in academic and technical research.

Updates

  • October 23, 2026: Stars 7,423 → 7,485, latest release v0.2.21 (October 23, 2026).
  • October 21, 2026: Stars 7,287 → 7,423, latest release v0.2.20 (October 21, 2026).
  • October 16, 2026: Stars 6,791 → 7,287, latest release v0.2.19 (October 15, 2026).
  • October 9, 2026: Stars 6,690 → 6,791, latest release v0.2.18 (October 9, 2026).

What you get

  • Creates independent and parallel agent sessions for different research ideas.
  • Provides traceability by keeping experiment results, logs, and code changes together.
  • Autonomously manages research cycles on your local computer or remote servers.

Installation

Installation on macOS or Linux
curl -LsSf https://openresearch.sh/install.sh | sh

Running it

Launch local dashboard
orx up

If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

I want to start a research project on OpenResearch. Using an AI agent like Claude Code or OpenCode, I want you to conduct a literature review, develop hypotheses, and design experiments to test these hypotheses. Throughout the study, manage the process autonomously by recording all findings, experiment results, and code changes in the OpenResearch local workspace.

Repository: https://github.com/alphaXiv/OpenResearch. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

Related dictionary terms

Who it is forSuitable for researchers who want to automate data collection, experimentation, and literature review processes in their academic or technical research.
LicenseMIT

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-09-12: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.