ai-agent

PaperForge: Accelerate Academic Paper Creation with AI

Name: PaperForge: Accelerate Academic Paper Creation with AI
Author: QJHWC

PaperForge lets founders generate ideas, run experiments, and compile LaTeX papers automatically—ideal for research‑driven startups seeking fast, AI‑assisted publishing.

From the repo · “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.”

638 stars+2★ this week95 forksPythonGuide quality 9/10 · reviewed Oct 11Updated 10/13/2026100% free · open source

What it does

PaperForge is an AI-powered system that automates the entire academic paper writing process, from idea generation to LaTeX paper compilation.

When to use it

•When you need to generate research papers quickly and efficiently
•When you want to explore multiple ideas and literature sources for your research
•When you need to automate the process of executing experiments and filling in results for your paper

Ready-to-paste prompt

python paper_forge.py --generate_idea --topic 'AI applications in healthcare' --num_papers 5

Heads up: Make sure you have the necessary dependencies installed, including Python 3.8 or later, and a compatible SSH client for remote training, and also be aware that the tool may require significant computational resources for large-scale paper generation

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/paperforge && curl -fsSL https://workflowstacks.com/api/skills/paperforge/claude-skill -o ~/.claude/skills/paperforge/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How PaperForge: Accelerate Academic Paper Creation with AI works

Codeflow

Free to inspect

PaperForge: Accelerate Academic Paper Creation with AI is a large Python project (~52k lines across 135 code files, plus 74 test files). Setup is light: runs with Docker. Last commit this month, Other license, has a test suite.

Size

Large codebase

~52k lines · 135 code files · ~7 h to skim

Setup

Light setup

Runs with Docker.

Runs on

Python · Docker

No API keys detected

Python 87%TeX 10%JavaScript 1%BibTeX Style 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
paperforge/cli.py
Where the program starts running
3
pyproject.toml
Dependencies and the commands it exposes
4
paperforge/__init__.py
Inside paperforge/ — the main logic begins here

What's in each folder

paperforge/Core code — the actual logic81 files

skills/Prompts, skills & agent definitions31 files

agents/Prompts, skills & agent definitions11 files

frontend/Frontend / UI4 files

templates/Templates10 files

docs/Documentation8 files

engine/Folder35 files

mcp_servers/Folder9 files

READMEHas testsDocumentedCI checksDocker readyOther licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/paperforge && curl -fsSL https://workflowstacks.com/api/skills/paperforge/claude-skill -o ~/.claude/skills/paperforge/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

QJHWC

Language

Python