PhilLit

PhilLit generates analytical literature reviews with verified bibliographies for philosophy research. Give it a topic description, and it searches academic databases, collects and checks references, and writes a structured review — typically in half an hour.

PhilLit is free and open-source. You only pay Anthropic for using Claude. This is a research project evaluating AI-generated literature reviews for philosophy (see below).

Example Reviews

• Extended Mind and Cognitive Offloading
• Metaphilosophy of Literature Reviews
• Moral Value of DIY

Highlights

• Searches multiple academic databases — Semantic Scholar, PhilPapers, SEP, IEP, OpenAlex, CORE, arXiv, and NDPR
• Checks every reference — All citations are sourced from academic databases (not generated by the LLM) and validated against CrossRef
• Produces a structured review with a bibliography you can import into Zotero, BibDesk, or any reference manager
• Outputs a Word document and a BibTeX file ready for reference managers or LaTeX

What does it cost?

PhilLit itself is free. Running it requires Claude Code, which needs a subscription or API access. Each literature review uses roughly $9 to $13 in API credits, depending on whether you use Sonnet or Opus.

Quick Start

What you need:

• Claude Code — the AI coding tool that runs PhilLit
• A Brave Search API key (free tier available)
• Optionally, a Semantic Scholar API key (free) for better search results

Setup takes about 10 minutes. See GETTING_STARTED.md for step-by-step instructions.

Once set up, describe your topic and PhilLit does the rest (~45 minutes):

I need a literature review on [topic].

[Describe the topic in 1-5 paragraphs]

What does it look like?

PhilLit running a literature review. The system decomposes the topic into research domains and searches multiple academic databases in parallel.

How It Works

1. Plan — Breaks your topic into searchable research domains
2. Research — Searches academic databases for each domain, collects and verifies references
3. Outline — Designs the structure of the review based on the collected literature
4. Write — Drafts each section of the review
5. Assemble — Combines sections into a final document with a complete bibliography

Development

• Instructions on contributing: CONTRIBUTING.md
• Agent architecture: .claude/docs/ARCHITECTURE.md
• Claude instructions: CLAUDE.md

Output Structure

Each review is saved in its own directory under reviews/:

reviews/[topic]/
├── literature-review-final.md        # Complete review (markdown)
├── literature-review-final.docx      # Complete review (Word, requires pandoc)
├── literature-all.bib                # Aggregated bibliography
└── intermediate_files/
    ├── json/                         # API response files (archived)
    ├── lit-review-plan.md            # Domain decomposition
    ├── literature-domain-*.bib       # Per-domain BibTeX files
    ├── synthesis-outline.md          # Review structure
    ├── synthesis-section-*.md        # Individual sections
    └── task-progress.md              # Progress tracker

Participate in Research

We're conducting validation studies (pending IRB approval) to rigorously assess whether PhilLit meets the standards required for serious philosophical research.

• Study 1: Use PhilLit on topics you already know well. We provide technical support and cover API costs.
• Study 2: Review literature overviews generated by others (no technical setup required).

Interested in participating? Sign up here and we'll notify you when the studies launch.

Contact

• Johannes Himmelreich — Syracuse University — jrhimmel@syr.edu
• Marco Meyer — University of Hamburg — marco.meyer@uni-hamburg.de

---

Inspired by LiRA multi-agent patterns.