HomeProjectsArticlesPK BoardAbout
Explore Projects

PPT Master

Active
GitHub Python MIT

Description

AI-powered PPT generation tool that creates natively editable PPTX from any document, producing real PowerPoint shapes instead of images.

Key Features

  • Native PPTX generation — produces real PowerPoint shapes instead of images, fully editable in PowerPoint
  • Document input parsing — supports Markdown, PDF, Word and other formats auto-parsed into slides
  • Multi-style templates — built-in Swiss Grid, Glassmorphism, Memphis Pop and other professional design styles
  • Speaker notes and narration — auto-generates speaker notes, exports narrated PPTX for direct playback
  • LLM-driven layout — uses AI for automatic layout design, color schemes and visual hierarchy
  • CLI and Web interfaces — supports command-line batch generation and online preview editing

Use Cases

💡 Convert technical docs or research reports into presentable PPTX slides quickly
💡 Auto-generate meeting presentations from Markdown notes
💡 Batch produce standardized demos for product intros, project reports and more
💡 Convert academic papers into narrated playable presentations
💡 Generate演讲 materials with data charts and visual layouts for content creators

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (51.5k stars)
  • • Permissive open-source license (MIT)
  • • Responsive to issues, low backlog

Tags

browser python agent automation tools

Categories

🌐 Browser Agent

Quick Start

pip install ppt-master
ppt-master generate --input report.md --output slides.pptx --style swiss-grid
Visit GitHub Visit Website

Related Projects

Index

2.4k · Python
Stale B

The SOTA open-source browser agent for autonomously performing complex tasks on the web with natural language-driven web automation.

pythonbrowseragent +2
  • · SOTA browser agent — autonomously navigates and interacts with websites using reasoning LLMs with vision
  • · Multi-model support — works with Gemini 2.5 Pro, Claude 3.7 Sonnet, and OpenAI o4-mini
  • · Structured output — extract data reliably using Pydantic schemas for programmatic consumption
View on GitHub

Scrapling

78.1k · Python
Active A+

An adaptive web scraping framework that intelligently handles anti-bot measures, from single requests to full-scale crawls, designed for AI agent data collection.

browserpythontools +2
  • · Adaptive selectors — Parser learns from website structure changes and automatically relocates elements when pages update
  • · Anti-bot bypass — Built-in StealthyFetcher and DynamicFetcher bypass Cloudflare Turnstile and other anti-bot systems
  • · Multi-mode fetchers — Fetcher, AsyncFetcher, StealthyFetcher, and DynamicFetcher for different scraping scenarios
View full details → View on GitHub

ScaleCUA

1.1k · Python
Stale C

Open-sourced computer use agents that can operate on cross-platform environments including Windows, macOS, Ubuntu, and Android. ICLR 2026 Oral paper project.

browserpythonagent +1
  • · Cross-platform GUI operation: supports Windows, macOS, Ubuntu, Android, and Web environments
  • · Large-scale training data: operation trajectories across 6 operating systems and 3 task domains
  • · State-of-the-art performance: MMBench-GUI L1-Hard 94.4%, OSWorld-G 60.6%, WebArena-Lite-v2 47.4%
View on GitHub