This repo runs a GitHub Action once a week (or on-demand) that:
- pulls new items from a list of journal RSS feeds
- triages items against your research interests (OpenAI API or Cursor CLI)
- writes a ranked digest to
digest.mdand commits it back to the repo
It’s meant to be forked and customized.
digest.py— pipeline (fetch RSS → filter → triage → render markdown)integrations/— optional Cursor CLI triage backend (default: in-file OpenAI in digest.py)feeds.txt— RSS feed list (comments; optionalName | URL)interests.md— keywords + narrative (used for relevance)prompt.txt— prompt template (used by OpenAI and Cursor backends)digest.md— generated output (auto-updated).github/workflows/weekly-digest.yml— scheduled GitHub Actionrequirements.txt— Python dependencies.python-version— pinned Python version (used by uv, pyenv, etc.)
Python version is pinned in .python-version (e.g. 3.11). The repo supports uv for fast, reproducible installs:
# Install uv (https://docs.astral.sh/uv/getting-started/installation/), then:
uv venv
uv pip install -r requirements.txt
uv run python digest.pyAlternatively use pip and a venv as usual; the GitHub workflow uses uv and reads .python-version.
- Fork the repo.
- Set
OPENAI_API_KEY(get one from platform.openai.com). Never commit it. - Locally: copy
.env.exampleto.env, add your key, runpython digest.py. - For GitHub Actions: add secret
OPENAI_API_KEYin Settings → Secrets. The workflow will use it; no CLI needed.
- Fork the repo.
- Install the Cursor CLI and set
CURSOR_API_KEY(Cursor settings). - For GitHub Actions: add secret
CURSOR_API_KEYand keep the workflow’s Cursor install step.
Backend is auto-chosen from which key is set, or set TOCIFY_BACKEND=openai or cursor to force.
Edit feeds.txt.
You can use comments:
# Core journals
Nature Neuroscience | https://www.nature.com/neuro.rss
PLOS Biology | https://journals.plos.org/plosbiology/rss
# Preprints
bioRxiv neuroscience | https://www.biorxiv.org/rss/subject/neuroscience.xml