Deep Researcher banner
jackswl jackswl

Deep Researcher

Development community

Description

Deep Research based on Claude Code's agentic framework 🦉⚡ export const SPINNER_VERBS = [ 'Accomplishing', 'Actioning', 'Actualizing', 'Architecting', 'Baking', 'Beaming', "Beboppin'", 'Befuddling', 'Billowing', 'Blanching', 'Bloviating', 'Boogieing', 'Boondoggling', ...]

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

Deep Researcher  Deep Researcher

Search Google Scholar, enrich with OpenAlex, synthesize structured literature reviews — all locally.

Python 3.10+ License: MIT Version: 0.5.0

Quick Start · How It Works · Sample Output · Configuration


Deep Researcher searches **Google Scholar** for academically-ranked papers, enriches them with full metadata from **OpenAlex**, and uses a local LLM to write a **structured literature review** with consistent citations.

  • 100 papers from Google Scholar's semantic search, no keyword hacks, no irrelevant results
  • Full metadata: DOIs, abstracts, journal names, citation counts, open access URLs
  • Structured synthesis: papers categorized by theme, with per-category analysis and cross-category patterns
  • Consistent [N] citations: every reference in the text matches the reference list
  • BibTeX + CSV output ready for LaTeX/Overleaf or Excel
  • Runs locally with Ollama. Your queries never leave your machine
  • Tool-based agentic architecture inspired by Claude Code
  • 4 dependencies, no LangChain

Quick Start

git clone https://github.com/jackswl/deep-researcher.git
cd deep-researcher
pip install -e .

Run with Ollama (local, free, private)

ollama pull qwen3.5:9b
deep-