daily-paper-digest

📚 Daily AI Paper Digest

Automatically fetches the latest AI papers from arXiv and HuggingFace every day, formats them, and pushes them to your chat app (Feishu, Slack, Discord, etc.).

Tools

fetch_daily_papers

Get today's latest paper digest.

Usage:

python3 main.py

Parameters:

• None (automatically reads the configuration in config/sources.json )

Returns:

• A formatted paper list, including title, authors, abstract, and link

---

search_arxiv_papers

Search arXiv papers on a specific topic.

Usage:

python3 arxiv_fetcher.py

Parameters (modify in the code):

• query: search keywords, such as "large language model"
• max_results: maximum number of results (default 5)

Returns:

• A list of matching papers

---

fetch_huggingface_papers

Get HuggingFace's daily trending papers.

Usage:

python3 huggingface_fetcher.py

Parameters:

• None (directly scrapes https://huggingface.co/papers）

Returns:

• A list of trending papers, including the number of likes

---

Configuration

Edit config/sources.json to customize information sources and filtering rules:

{
  "sources": [
    {
      "name": "arxiv",
      "enabled": true,
      "categories": ["cs.AI", "cs.CL", "cs.CV", "cs.LG"],
      "max_results": 10
    },
    {
      "name": "huggingface",
      "enabled": true,
      "max_results": 10
    }
  ],
  "filter": {
    "keywords": ["LLM", "transformer"],
    "exclude_keywords": []
  }
}

Common arXiv categories

Code	Meaning
cs.AI	Artificial Intelligence
cs.CL	Computational Linguistics/NLP
cs.CV	Computer Vision
cs.LG	Machine Learning
cs.NE	Neural Networks
cs.RO	Robotics
stat.ML	Statistical Machine Learning

---

Installation and Usage

1. Install dependencies

pip3 install -r requirements.txt

2. Run tests

python3 test.py

3. Get today's papers

python3 main.py

4. Run automatically on a schedule (with the OpenClaw scheduler)

Configure a Cron expression in OpenClaw (for example, daily at 9:00):

0 9 * * *

---

Trigger in OpenClaw

Send any of the following in the chat app to trigger it:

• 论文速递
• 今日论文
• 最新论文
• /papers
• /digest

---

Dependencies

• arxiv — arXiv official Python client
• requests — HTTP requests
• beautifulsoup4 — HTML parsing
• feedparser — RSS/Atom parsing

---

Example Output

╔══════════════════════════════════════════════════════════╗
║           🎓 AI 论文每日速递 - 2026年02月20日           ║
╚══════════════════════════════════════════════════════════╝

📊 今日共收录 15 篇论文

============================================================
📄 论文 1
============================================================

📌 标题: Attention Is All You Need
👥 作者: Ashish Vaswani, Noam Shazeer 等 8 人
🏷️  来源: ARXIV | 日期: 2026-02-20

📝 摘要:
The dominant sequence transduction models are based on...

🔗 arXiv: http://arxiv.org/abs/1706.03762
📥 PDF: http://arxiv.org/pdf/1706.03762

---

File Structure

daily-paper-digest/
├── SKILL.md                 ← 本文件（ClawHub 规范）
├── main.py                  ← 主程序
├── arxiv_fetcher.py        ← arXiv 模块
├── huggingface_fetcher.py  ← HuggingFace 模块
├── requirements.txt        ← Python 依赖
└── config/
    ├── sources.json        ← 默认配置
    └── sources_llm.json    ← LLM 专用配置