QJHWC

QJHWC / PaperForge

Public

End-to-end AI-powered academic paper writing system — from idea generation and literature search to experiment execution, result backfill, and LaTeX paper compilation. Supports multi-LLM routing, SSH remote training, incremental sync, and anti-AI-detection writing style.

github.comSakanaAIAI-Scientist academic-writing ai latex llm paper-generation
16
4
100% credibility
Found Mar 06, 2026 at 16 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

PaperForge automates the full process of generating academic papers using AI for ideas, experiments, writing, review, and optional remote training.

How It Works

1
🔍 Discover PaperForge

You find this helpful tool that uses smart helpers to automatically create full academic papers from ideas to experiments and drafts.

2
⚙️ Get ready

You download it, connect friendly AI thinkers for different tasks like ideas and writing, and prepare a simple note about your topic.

3
✨ Create your first draft

With one command, it generates fresh research ideas, runs simple tests, searches for related work, and builds your initial paper PDF.

4
📤 Add your insights

You upload notes, new test results, or pictures, and it weaves them into the paper, updating everything smoothly.

5
🔄 Improve and expand

It runs more tests, updates charts, polishes the writing deeply, and checks itself like a journal reviewer.

6
Need heavy computing?
🚀
Use cloud power

It safely sends files, runs on the server, pulls results back, and blends them into your paper.

✅
Stay local

Finalize without remote, keeping everything on your machine.

📄 Your paper is ready

You get a complete, polished PDF with stats, charts, and required AI notes, ready to review or submit.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 16 to 16 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is PaperForge?

PaperForge is an AI-powered end-to-end solution for generating academic papers, handling everything from idea brainstorming and literature searches via OpenAlex/Semantic Scholar to running experiments, aggregating stats with significance tests, and compiling LaTeX PDFs. Built in Python, it supports multi-LLM routing—route Grok for creative ideas, Claude for polished writing—and SSH remote training on GPU servers with automatic result syncing. Users get iterative workflows that produce disclosure-ready manuscripts with anti-AI-detection styles.

Why is it gaining traction?

It stands out as an end-to-end LLM project that closes the loop on research: local prototyping scales seamlessly to remote GPUs via simple YAML configs, with quality gates and watchdogs preventing wasted cycles. Developers love the phased CLI entry points for controlled iteration—bootstrap a draft, feedback on uploads, optimize experiments—plus cost-optimized prompts that cut token burn by 80% versus upstream tools. No more manual LaTeX fixes or stats drudgery.

Who should use this?

ML researchers prototyping conference submissions, PhD students automating baselines and ablations, or academics in data-heavy fields like CV/NLP needing quick Pareto fronts and t-tests. Ideal for those with SSH access to GPUs who want an end-to-end data science project GitHub-style but laser-focused on paper output.

Verdict

Promising for AI-powered academic workflows, but at 16 stars and 1.0% credibility, it's early—expect rough edges in edge cases despite solid docs and Docker support. Try for MVP papers if you're okay forking a SakanaAI derivative; skip for production pipelines.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.