DreamPaper is a local tool for creating scientific figures and academic slides from templates in one step.

Stars

10

7-day growth

No data

Forks

2

Open issues

0

License

No data

Last updated

2026-07-29

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It combines template-driven few-shot generation for figures and master-slide driven layout for presentations, supports multiple model APIs, and keeps all data local for privacy.

Who it is for

  • Researchers needing quick publication-ready figures
  • Academics preparing slide decks for conferences
  • Students who want to automate repetitive chart and slide creation

Use cases

  • Generate scientific diagrams and plots from reference templates
  • Create branded slide decks by uploading a master slide template
  • Automate the production of consistent visual assets for a paper or presentation

Strengths

  • Fully local execution (config and outputs in ~/.dreampaper/, no API keys in the repo)
  • Two-stage pipeline separates structural extraction from content filling, reducing style drift
  • Flexible model selection (OpenAI, Anthropic, image2, banana2) with distinct modes for Design/Implement/Search
  • Slide visual grounding identifies products and instruments from source material to guide realistic rendering

Considerations

  • Requires downloading the external PaperBananaBench dataset (~266MB) for scientific figure mode
  • Depends on third-party API keys (OpenAI/Anthropic/etc.) for model access
  • Only supports Python 3.10+ and the specific frontend build (Vite 7, React 19), limiting deployment to local machines

README quick start

使用

Description

高质量科研论文插图与演示文稿制作Agent

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
MoonshotAI
Featured
MoonshotAI GitHub avatar

Kimi-K3

Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.

AI & Machine LearningAI Agents
3,348
mshumer
Featured
mshumer GitHub avatar

Claude-of-Duty

A browser-based first-person shooter built entirely with procedural generation and orchestrated AI agents, featuring 55k lines of Three.js/WebGL2 code and no art assets.

AI & Machine LearningAI Agents
1,234