Generate master-level research papers with real citations in minutes
Project description
OpenDraft Engine
The Python AI engine that powers thesis draft generation. Contains the 19-agent pipeline, citation research, and export functionality.
Structure
engine/
├── draft_generator.py # Main 19-stage pipeline orchestrator
├── config.py # Model settings, API keys, rate limits
├── utils/
│ ├── agent_runner.py # Agent execution engine
│ ├── api_citations/ # Citation APIs (CrossRef, Semantic Scholar)
│ ├── citation_*.py # Citation management & validation
│ ├── export_professional.py # PDF/DOCX export
│ ├── pdf_engines/ # Pandoc, WeasyPrint engines
│ └── deep_research.py # Research phase utilities
├── prompts/
│ ├── 00_WORKFLOW.md # Complete agent workflow
│ ├── 01_research/ # Deep Research, Scout, Scribe, Signal
│ ├── 02_structure/ # Architect, Citation Manager, Formatter
│ ├── 03_compose/ # Crafter, Thread, Narrator
│ ├── 04_validate/ # Skeptic, Verifier, Referee
│ ├── 05_refine/ # Citation Verifier, Voice, Entropy, Polish
│ └── 06_enhance/ # Abstract Generator, Enhancer
└── opendraft/ # CLI tools
Usage
Run Pipeline Directly
cd engine
python draft_generator.py --topic "Your research topic" --level master
Academic Levels
| Level | Words | Chapters | Time |
|---|---|---|---|
| research_paper | 3-5k | 3-4 | 5-10 min |
| bachelor | 10-15k | 5-7 | 8-15 min |
| master | 20-30k | 7-10 | 10-25 min |
| phd | 50-80k | 10-15 | 20-40 min |
Environment Variables
Required in .env (project root):
GEMINI_API_KEY=your-key # Required
PROXY_LIST=... # Optional: for faster research
SCOUT_PARALLEL_WORKERS=32 # Optional: parallelism
Dependencies
pip install -r requirements.txt
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
opendraft-1.6.25.tar.gz
(330.7 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
opendraft-1.6.25-py3-none-any.whl
(365.1 kB
view details)
File details
Details for the file opendraft-1.6.25.tar.gz.
File metadata
- Download URL: opendraft-1.6.25.tar.gz
- Upload date:
- Size: 330.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2cea34906eb375b74aa37bc4114ddeaa38f0a55af87ff0166ee61340853176bc
|
|
| MD5 |
7cc07ff4d589f3673a1eb761f2bc7b62
|
|
| BLAKE2b-256 |
78bd019547183e741a7b819d57e3bd2e6b874990c409f9a77d0ccf3002e2fc99
|
File details
Details for the file opendraft-1.6.25-py3-none-any.whl.
File metadata
- Download URL: opendraft-1.6.25-py3-none-any.whl
- Upload date:
- Size: 365.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f71b347e957dd370874bf6096852d9cf1b10fe0533c1d0619af8e7d163031ad5
|
|
| MD5 |
6241884a7c62e2862c3e3826f3c03c00
|
|
| BLAKE2b-256 |
18f7d2c3ba675ef03174796a76af6ed9520f57992a793f8938dfc02133304fdb
|