jxpeng98/qiongli

26 stars · Last commit 2026-10-09

穷理证澈 Academic Research Skills: Plan the work, search the literature, draft and review manuscripts, run research code, and keep the evidence trail in one place.

README preview

<div align="center">
  <h1>Qiongli (穷理)</h1>
  <p><strong>Use AI agents for research, with sources you can check.</strong></p>
  <p>Read papers, design studies and write with Codex, Claude Code or DeepSeek Harness. Keep your model settings and research records.</p>
  <p>
    <a href="https://www.npmjs.com/package/qiongli"><img alt="npm version" src="https://img.shields.io/npm/v/qiongli/latest?style=flat-square&amp;logo=npm"></a>
    <a href="https://pypi.org/project/qiongli/"><img alt="PyPI version" src="https://img.shields.io/pypi/v/qiongli?style=flat-square&amp;logo=pypi"></a>
  </p>
  <p><a href="README_CN.md">中文</a> · <a href="docs/index.md">Docs</a> · <a href="tooling/release/v2.5.1.md">2.5.1 release notes</a></p>
</div>

## Install

Download your platform's CLI from [Release v2.5.1](https://github.com/jxpeng98/qiongli/releases/tag/v2.5.1), verify its `SHA256SUMS`, and extract it. Run `./qiongli --version` (PowerShell: `.\qiongli.exe --version`). No Python, Node.js or Rust installation is needed.

Supports macOS ARM64, Windows x64, and Linux x64/ARM64 with glibc 2.35+. [Download and package-manager instructions](docs/guide/install.md).

With Node.js 18+, you can also install through npm:

```sh

View full repository on GitHub →