Back: Catalog

hyperresearch

It is a Python project that transforms Claude Code and OpenAI Codex vehicles into deep research tools. It offers a 16-step pipeline that runs on a single command prompt, verifies resources, and creates a permanent search repository. It can also be used with a hosted API and MCP support without requiring local installation.

HY

hyperresearch

New80

jordan-gibbs · Scientific Research & Computing

STARS4.2K
FORKS416
COMMITS0
CONTRIBUTORS0
VERSIONv0.12.0
UPDATEDtoday
PythonDeep ResearchClaude CodeOpenAI CodexMIT
What can it do?
  • You do web searches with a single command prompt and produce a deep-source research report.
  • You store all read sources in a permanent and searchable data repository.
  • You get access to scientific resources by questioning academic search engines.
User reviews
  • • NeutralGitHub Issue

    PDF extraction failures across independent mirrors trace to PyMuPDF parsing path

    “## Description During a large batch run, multiple PDF extraction failures occurred across distinct mirrors for the same documents. Four independent hosting mirrors produced byte-identical `pymupdf` extraction errors. Because identical failure signatures occurred across…”

  • ↓ NegativeGitHub Issue

    Capture bibliographic metadata (journal, DOI, year, preprint-vs-published) for paper notes

    “## Problem When a paper is fetched, the note only stores the raw `source:` URL, and `_detect_content_type` lumps everything into `content_type: paper`. So journal, volume, etc.. are never captured but arXiv preprint is indistinguishable from a peer-reviewed journal article. That…”

Website GitHub

My note

More in: Scientific Research & Computing