Skip to main content

A CLI tool to analyze academic papers and extract their core value

Project description

Paper Fluff Cutter

A CLI tool that cuts through academic paper fluff to extract what actually matters.

Most research has close to zero value. This tool uses multimodal LLMs to analyze papers and answer three questions:

  1. Why should I care? - What problem does this address and why does it matter?
  2. What's the actual innovation? - What's the core idea in plain terms?
  3. Is the evidence convincing? - Do the experiments actually support the claims?

Quick Start

pip install fluff-cutter
fluff-cutter init          # set up API keys and defaults
fluff-cutter analyze paper.pdf

Requires Python 3.10+.

Usage

# Local file
fluff-cutter analyze paper.pdf

# URL (arxiv /abs/ links are auto-converted to PDF)
fluff-cutter analyze https://arxiv.org/pdf/2411.19870

# Options
fluff-cutter analyze paper.pdf --output analysis.md   # custom output path
fluff-cutter analyze paper.pdf --print                 # stdout only, no file
fluff-cutter analyze paper.pdf --provider openai       # openai, anthropic, openrouter
fluff-cutter analyze paper.pdf --model gpt-5.2         # override default model
fluff-cutter analyze paper.pdf --max-pages 30          # limit pages for long papers

By default, results are printed to the terminal and saved as a .md file next to the input PDF. Model output streams live during analysis (provider-side streaming), so you see tokens immediately instead of waiting for full completion.

Supported Providers

Provider Default Model Env Variable
OpenAI gpt-5.2 OPENAI_API_KEY
Anthropic claude-sonnet-4-5 ANTHROPIC_API_KEY
OpenRouter anthropic/claude-sonnet-4-5 OPENROUTER_API_KEY

All providers support native PDF input -- no external dependencies like poppler needed.

Configuration

Run fluff-cutter init for interactive setup, or set environment variables directly:

export OPENAI_API_KEY=sk-your-key-here
export FLUFF_CUTTER_PROVIDER=anthropic          # default provider
export FLUFF_CUTTER_ANTHROPIC_MODEL=claude-sonnet-4-5  # override model

Config is read in this order (highest priority first): CLI flags, env variables, ~/.fluff-cutter/config.yaml, provider defaults.

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

fluff_cutter-0.4.2.tar.gz (21.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

fluff_cutter-0.4.2-py3-none-any.whl (18.0 kB view details)

Uploaded Python 3

File details

Details for the file fluff_cutter-0.4.2.tar.gz.

File metadata

  • Download URL: fluff_cutter-0.4.2.tar.gz
  • Upload date:
  • Size: 21.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for fluff_cutter-0.4.2.tar.gz
Algorithm Hash digest
SHA256 6962af2d829b86634b19d93a6fa226a1337860ec0e923b918177c5ae830c731e
MD5 351fd3b3698689330aab445a4d7515e2
BLAKE2b-256 dbbbd522c54d573a628fce1a9b07223e5d4893588d6646d2c810e126c5a196fa

See more details on using hashes here.

Provenance

The following attestation bundles were made for fluff_cutter-0.4.2.tar.gz:

Publisher: publish.yml on weijianzhg/paper-fluff-cutter

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file fluff_cutter-0.4.2-py3-none-any.whl.

File metadata

  • Download URL: fluff_cutter-0.4.2-py3-none-any.whl
  • Upload date:
  • Size: 18.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for fluff_cutter-0.4.2-py3-none-any.whl
Algorithm Hash digest
SHA256 6a7f5d11ba8543db7b3eed75bff62f3774095f729fba64d81f97e4828bf3681f
MD5 81685336740ffc327c1d4f9cd13d9cf5
BLAKE2b-256 ba457b9b113702d6aac9cab7633282cb777470f60b11a0699048f0135f15b4f9

See more details on using hashes here.

Provenance

The following attestation bundles were made for fluff_cutter-0.4.2-py3-none-any.whl:

Publisher: publish.yml on weijianzhg/paper-fluff-cutter

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page