zhanglg12

zhanglg12 / research-assist

Public

Lightweight arXiv literature digest skill for OpenClaw — Zotero-driven interest profiling, 3-dimensional candidate ranking, abstract-first review

16
0
100% credibility
Found Mar 16, 2026 at 16 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

research-assist reads your Zotero library to build a research profile, searches arXiv for matching papers, ranks and enriches them into a digest delivered by email or Telegram, and supports feedback to update your library.

How It Works

1
📚 Discover research helper

You hear about a simple tool that finds new research papers based on papers you've already saved and loved.

2
🛠️ Set it up quickly

Tell your AI assistant or follow easy steps to get the tool ready on your computer.

3
🔗 Link your paper collection

Connect your personal library of saved papers so it understands what topics excite you.

4
🧠 Build your interest map

The tool scans your collection, tags, and notes to create a snapshot of your research tastes.

5
🔍 Run your first search

With one command, it searches for fresh papers matching your unique profile.

6
📧 Get your weekly digest

Open your email or messages to see a beautiful summary of top picks with reasons why they fit.

🌟 Research flows effortlessly

New ideas arrive automatically, you mark favorites, and your library grows smarter over time.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 16 to 16 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is research-assist?

This Python tool acts as a lightweight research assistant, pulling your interests directly from Zotero collections, tags, and papers to build a profile, then querying arXiv for fresh matches. It ranks candidates using 3-dimensional scoring—research-map alignment, Zotero semantic similarity, and recency—before generating abstract-first digests with AI-enriched reviews. Output lands as clean HTML, email, or Telegram messages, with optional feedback syncing tags and notes back to Zotero.

Why is it gaining traction?

Unlike keyword-driven tools, it leverages your existing library for precise, personalized retrieval without manual setup, closing the loop by improving Zotero over time. The agent-native design slots into OpenClaw, Claude Code, or any LLM CLI, with simple actions like `uv run research-assist --action digest`. As a lightweight GitHub project, it skips heavy dependencies, focusing on fast pipelines and beautiful, mobile-ready outputs that feel like a personal research assistant AI.

Who should use this?

Academic researchers, PhD students, or research assistants—think psychology profs tracking niche papers, remote research assistant jobs scanning arXiv daily, or students building lit reviews. It's ideal if you hoard Zotero items but drown in feeds, needing a 3-dimensional filter before diving in.

Verdict

Try it if Zotero + arXiv is your workflow; the CLI shines for automation. With 16 stars and 1.0% credibility, it's early-stage—solid docs but light tests—so test locally first. Niche win for solo academics.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.