OpenDraft - Open Source AI Research Draft Generator

Generate research drafts with citations verified against 250M+ academic papers. OpenDraft is a free, open-source Python engine for thesis-level research drafts.

<p align="center"> <a href="https://opendraft.xyz/waitlist"><strong>Try Hosted Version (Coming Soon) →</strong></a> </p>

What is OpenDraft?

OpenDraft is a Python-based AI engine that generates thesis-level research drafts. Unlike ChatGPT, it uses 19 specialized AI agents working together and verifies every citation against real academic databases.

Best for: Researchers drafting literature reviews, research papers, and academic documents
Price: 100% free and open source (MIT license)
Setup time: 10 minutes

Why OpenDraft Exists

We built OpenDraft after repeatedly encountering AI writing tools that produced confident-sounding research drafts with hallucinated or unverifiable citations.

Academic research requires trust, sources, and accountability.

OpenDraft explores a different approach: instead of a single general-purpose model, it uses multiple specialized agents, each responsible for a specific step in the research drafting process, grounded in real academic literature.

We open-sourced OpenDraft so researchers can inspect, critique, and improve how these systems actually work.

What OpenDraft is NOT

OpenDraft is intentionally not designed for:

One-click generation of final papers
Cheating on assignments
Inventing citations or bypassing peer review
Replacing human researchers

It is a research assistance and drafting tool, not an autonomous author.

OpenDraft vs ChatGPT

| Question | ChatGPT | OpenDraft | |----------|---------|-----------| | Does it hallucinate citations? | Yes (often) | Verified against real databases | | Can it write 20,000+ words? | No (hits limits) | Yes | | Does it search real papers? | No | Yes (250M+ papers) | | Thesis structure? | Generic | Academic chapters & sections | | Export to PDF/Word? | No | Yes | | Free? | Limited | 100% free (self-host) | | Open source? | No | Yes (MIT license) |

Bottom line: If you need an AI for academic writing with real citations, OpenDraft is a free, open-source alternative to ChatGPT.

How It Works

OpenDraft uses 19 specialized AI agents that work like a research team:

📚 RESEARCH PHASE    → Finds relevant papers from 250M+ sources
🏗️ STRUCTURE PHASE   → Creates thesis outline with chapters
✍️ WRITING PHASE     → Drafts each section with academic tone
🔍 CITATION PHASE    → Verifies every source exists (CrossRef, arXiv)
✨ POLISH PHASE      → Refines language and formatting
📄 EXPORT PHASE      → Generates PDF, Word, or LaTeX

Result: A complete research draft in 10-20 minutes instead of weeks.

Features

AI That Doesn't Make Up Citations

Every citation is verified against CrossRef, OpenAlex, Semantic Scholar, and arXiv. If a paper doesn't exist, it's not included.

Write Any Type of Academic Paper

Research papers (5-10 pages)
Bachelor's thesis (30-50 pages)
Master's thesis (50-80 pages)
PhD dissertation (100+ pages)

57+ Languages Supported

English, Spanish, German, French, Chinese, Japanese, Korean, Arabic, Portuguese, Italian, Dutch, Polish, Russian, and 40+ more.

Export to Any Format

PDF - LaTeX-quality formatting
Microsoft Word (.docx)
LaTeX source - for journals

100% Free and Open Source

MIT license. Self-host with your own API keys. No subscriptions, no paywalls, no limits.

TL;DR and Digest Tools

OpenDraft includes two standalone tools for quickly understanding any research paper:

TL;DR: 5-Bullet Summary

Generate a concise 5-bullet summary of any paper in seconds:

# As a subcommand
opendraft tldr paper.pdf

# Or standalone
opendraft-tldr paper.pdf

# Output to file
opendraft tldr paper.pdf -o summary.md

Each bullet follows academic structure: thesis, key finding, method, implication, limitation.

Digest: 60-Second Audio Briefing

Generate a podcast-style audio summary you can listen to:

# Generate script + audio
opendraft digest paper.pdf

# Choose a different voice (rachel, adam, josh, elli, bella)
opendraft digest paper.pdf --voice adam

# Script only (no audio)
opendraft digest paper.pdf --no-audio

# Specify output directory
opendraft digest paper.pdf -o output/

Requirements:

Digest audio requires an ElevenLabs API key set as ELEVENLABS_API_KEY
PDF reading requires the optional pdf extra: pip install opendraft[pdf]

Both tools work with any academic paper (PDF, Markdown, or plain text), not just OpenDraft-generated documents.

Data Fetching

Fetch research data from major statistical APIs directly into your workflow:

# Search for indicators
opendraft data search GDP

# Fetch World Bank data
opendraft data worldbank NY.GDP.MKTP.CD --countries USA;DEU --start 2020 --end 2023

# Fetch EU statistics (Eurostat)
opendraft data eurostat nama_10_gdp

# Fetch Our World in Data datasets
opendraft data owid covid-19

Supported providers:

World Bank - Development indicators (GDP, population, education, health)
Eurostat - European Union statistics
Our World in Data - Open research datasets

Data is saved as CSV files for use in your research.

Draft Revision

Revise existing drafts with AI assistance:

# Revise a draft with natural language instructions
opendraft revise ./output "Make the introduction longer and add more context"

# The revised draft is saved as draft_v2.md (with PDF/DOCX exports)

Features:

Auto-detects draft files in output folders
Preserves all citations during revision
Automatic versioning (v2, v3, v4...)
Quality scoring before/after
PDF and DOCX export of revised version

Research Expose Mode

Generate a quick research overview instead of a full draft:

opendraft "Neural Networks in Healthcare" --expose

This produces a research expose with:

Research Sources Overview - Number of sources, publication years, key journals
Key Research Teams - Major authors and research groups in the field
Structured Outline - Chapter/section structure for a full paper
Complete Bibliography - All sources with DOIs and journal info
Next Steps - Guidance for developing into a full draft

Use expose mode when you want to:

Quickly scope a research topic
Validate there's enough literature
Get a structured starting point
Review sources before committing to a full draft

Expose mode is ~3x faster than full draft generation.

TL;DR Mode

Generate a 5-bullet summary of any academic paper in seconds:

# Summarize a PDF
opendraft tldr paper.pdf

# Summarize a markdown file
opendraft tldr draft.md

# Save to file
opendraft tldr paper.pdf --output summary.md

Output:

📄 TL;DR: paper.pdf

• Main finding: Neural networks improve diagnostic accuracy by 23%
• Method: Retrospective analysis of 50,000 patient records
• Key limitation: Single-center study, needs external validation
• Implication: AI-assisted diagnosis could reduce misdiagnosis rates
• Future work: Multi-center trials planned for 2025

Works with any PDF, Markdown, or text file.

Audio Digest

Generate a 60-second audio summary using ElevenLabs TTS:

# Generate audio digest (requires ElevenLabs API key)
opendraft digest paper.pdf

# Choose a voice
opendraft digest paper.pdf --voice adam

# Available voices: rachel (default), adam, josh, elli, bella

Output: paper_digest.mp3 - a professional narration summarizing the key points.

Setup: Set ELEVENLABS_API_KEY in your environment or .env file.

Quick Start

Prerequisites

Python 3.10+
A free Gemini API key

1. Clone & Install

git clone https://github.com/federicodeponte/opendraft.git
cd opendraft
pip install -r requirements.txt

2. Configure

Create a .env file with your API key:

GOOGLE_API_KEY=your-gemini-api-key

3. Generate a Draft

from engine.draft_generator import DraftGenerator

generator = DraftGenerator()
draft = generator.generate(
    topic="The Impact of AI on Academic Research",
    paper_type="master",  # research_paper, bachelor, master, phd
    language="en"
)

# Export to different formats
draft.to_pdf("thesis.pdf")
draft.to_docx("thesis.docx")
draft.to_latex("thesis.tex")

See engine/README.md for detailed API documentation.

Which AI Model Should I Use?

| Model | Speed | Quality | Cost/Draft | Best For | |-------|-------|---------|------------|----------| | Gemini 3 Flash | ⚡ Fast | Good | ~$0.35 | Most users | | Gemini 3 Pro | Medium | Excellent | ~$1.40 | Important papers | | GPT-5.2 | Medium | Excellent | ~$1.60 | OpenAI users | | Claude Sonnet 4.5 | Medium | Excellent | ~$1.80 | Nuanced writing | | Claude Opus 4.5 | Slow | Best | ~$3.00 | Maximum quality |

Recommendation: Start with Gemini 3 Flash for most use cases. Use Gemini 3 Pro or Claude Sonnet 4.5 for important papers.

Example Output

See what OpenDraft produces:

📄 Download Sample PDF (60 pages, 18k words, 40+ citations)

📝 **[Download Sample Word](https://opendraft.xyz/examples/Why_Academic_Thesis_AI_Saves_The_

Opendraft

Install / Use

README