Ppt Master AI Agent

by hugohe3• 72k•• Scanned•Claim this listing•Request removal

Productivity & Workflowai agentaipptofficepowerpointpowerpoint generation

AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He

Ppt Master is an open-source ai agent by hugohe3, written mainly in Python, with 71,923 GitHub stars and the MIT license. Its code was last updated Oct 30, 2026.

about README security reviews

PPT Master — AI generates native PowerPoint from any document

English | 中文

💼 I'm open to new opportunities. Investment background (CPA · CPV · Consulting Engineer), also building AI tools and open source. Happy to talk about any opportunity: heyug3@gmail.com · hehugo.com.

🆕 I built a construction project economic evaluation site: cs.hehugo.com (in Chinese) — the wind, solar and storage templates are now open to everyone; just register and use them (a comparable module in one commercial package sells for ¥100,000).

❤️ Sponsors

This project is kept free and open source with the support of <a href="https://www.kimi.com/code/?aff=ppt-master">Kimi</a>, <a href="https://www.packyapi.ai/register?aff=ppt-master">PackyCode</a>, <a href="https://apikey.fan/register?aff=PPT-MASTER">APIKEY.FAN</a>, <a href="https://runapi.host/register?aff=WMLJ">RunAPI</a>, <a href="https://modelgo.ai/?utm_source=ppt-master&utm_medium=sponsorship&utm_content=readme01&campaign_id=ppt-master-github&ad_group_id=readme01">ModelGo</a> and other sponsors.

Want to appear here?

<details open> <summary>Click to collapse</summary> <a href="https://www.kimi.com/code/?aff=ppt-master"><img src="https://gcdn.moonshot.cn/growth-cdn/sponsor/kimi-en.png" alt="Kimi" width="100%"></a>

Thanks to Kimi for sponsoring this project! Kimi K3 is the world's first open 3T-class model, featuring native vision and a 1-million-token context window. With PPT Master, K3 can understand source materials such as PDFs, DOCX files, and web pages, identify key points, structure the narrative, and generate a natively editable PPTX that you can continue refining in PowerPoint.

Try a Kimi Code plan (中文站 | Global), or access the API through the Kimi Open Platform (中文站 | Global).

<hr> <table> <tr> <td width="180"><a href="https://www.packyapi.ai/register?aff=ppt-master"><img src="docs/assets/sponsors/packycode.png" alt="PackyCode" width="150"></a></td> <td>Thanks to PackyCode for sponsoring this project! PackyCode is a reliable and efficient API relay service provider, offering relay services for Claude Code, Codex, Gemini, and more. PackyCode provides special discounts for our project users: register using <a href="https://www.packyapi.ai/register?aff=ppt-master">this link</a> and enter the promo code ppt-master during recharge to get 10% off.</td> </tr> <tr> <td width="180"><a href="https://apikey.fan/register?aff=PPT-MASTER"><img src="docs/assets/sponsors/apikey-fan.png" alt="APIKEY.FAN" width="150"></a></td> <td>Thanks to APIKEY.FAN for sponsoring this project! APIKEY.FAN is a professional enterprise-grade AI relay service committed to stable, efficient, and low-cost AI access for businesses and developers. The platform supports mainstream models including Claude, OpenAI, and Gemini, with prices as low as 7% of official rates. Register through <a href="https://apikey.fan/register?aff=PPT-MASTER">our dedicated link</a> for an exclusive perk: up to 5% off on top-ups, permanently.</td> </tr> <tr> <td width="180"><a href="https://runapi.host/register?aff=WMLJ"><img src="docs/assets/sponsors/runapi.png" alt="RunAPI" width="150"></a></td> <td>Thanks to RunAPI for sponsoring this project! RunAPI is an efficient and stable API platform — a single API Key gives you access to 150+ leading models, including OpenAI, Claude, Gemini, DeepSeek, and Grok, at prices as low as 10% of official rates, with exceptional stability and seamless compatibility with tools like Claude Code. RunAPI offers an exclusive perk for PPT Master users: register and contact an administrator via <a href="https://runapi.host/register?aff=WMLJ">our dedicated link</a> to claim ¥7 in free credit.</td> </tr> <tr> <td width="180"><a href="https://modelgo.ai/?utm_source=ppt-master&utm_medium=sponsorship&utm_content=readme01&campaign_id=ppt-master-github&ad_group_id=readme01"><img src="docs/assets/sponsors/modelgo.svg" alt="ModelGo" width="150"></a></td> <td>Thanks to ModelGo for sponsoring this project! ModelGo is a stable, efficient enterprise-grade AI API aggregation platform. A single API Key gives you access to leading AI models including Claude, OpenAI, Gemini, and DeepSeek, helping developers and businesses build AI applications quickly at lower cost. ModelGo offers an exclusive perk for PPT Master users: get $0.5 in trial credit on sign-up, another $2 after your first API call, and an extra $1 for inviting new users! The platform also offers a tiered spending rebate: the more you use, the more you get back, so you can enjoy AI model calls to the fullest. In addition, ModelGo supports enterprise-grade features such as SLA service guarantees and visual monitoring dashboards, keeping API calls stable and reliable for production deployments. Visit the <a href="https://modelgo.ai/?utm_source=ppt-master&utm_medium=sponsorship&utm_content=readme01&campaign_id=ppt-master-github&ad_group_id=readme01">ModelGo website</a> to sign up and start building AI efficiently!</td> </tr> </table> </details>

Editable is already table stakes — what sets PPT Master apart is native depth. It delivers a real PowerPoint: slide masters, native shapes, and data-backed charts and tables — neither flat text boxes nor a filled-in template. It structures your argument first and designs page by page second, while continuously converging with PowerPoint itself as new native capabilities land each release. In form, it's a local workflow that runs inside any agent-capable AI tool: hand the AI your topic or source files and get a .pptx generated on your machine — local data, no platform or model lock-in. How it works and where the limits are → Product Positioning.

<a href="#quick-start">Quick Start</a> · <a href="https://hugohe3.github.io/ppt-master-examples/">Live Demo</a> · <a href="https://github.com/hugohe3/ppt-master-examples">Examples</a> · <a href="./docs/faq.md">FAQ</a> · <a href="./docs/roadmap.md">Roadmap</a> <table> <tr> <td align="center" width="33%"> <a href="https://hugohe3.github.io/ppt-master-examples/viewer.html?project=ppt169_pixel_breakfast_atlas"><img src="docs/assets/screenshots/preview_pixel_breakfast_atlas.webp" alt="Pixel art — Chinese breakfast atlas" /></a> Pixel Art — Chinese breakfast atlas: AI sprite sheets, HUD panels, Morph and 8-bit sound cues </td> <td align="center" width="33%"> <a href="https://hugohe3.github.io/ppt-master-examples/viewer.html?project=ppt169_attention_is_all_you_need"><img src="docs/assets/screenshots/preview_attention_is_all_you_need.webp" alt="Technical blueprint — Attention Is All You Need" /></a> Technical Blueprint — Transformer paper walkthrough: diagrams, native formulas, notes and animations </td> <td align="center" width="33%"> <a href="https://hugohe3.github.io/ppt-master-examples/viewer.html?project=ppt169_china_telecom_2025"><img src="docs/assets/screenshots/preview_china_telecom_2025.webp" alt="Brand template — China Telecom 2025 results" /></a> Brand Template — China Telecom 2025 results on the company's own deck template, with a native-chart export </td> </tr> </table> Every example is a single pass with no manual polish; downloading a .pptx and opening it in PowerPoint is the fastest way to see what it can really do. <a href="https://hugohe3.github.io/ppt-master-examples/">Flip through all examples online →</a> · <a href="https://github.com/hugohe3/ppt-master-examples">Source repository</a> · <a href="./docs/why-ppt-master.md">Why PPT Master?</a>

Product Positioning

Native depth means how much of PowerPoint's real object model you actually get. Native shapes and connectors with live adjustment handles, data-backed charts and tables on demand, and the full text, picture, fill, and effect system — click any element and edit it as a first-class PowerPoint object. Through the template or structured route, it also produces decks with real slide masters and layouts (p:sldMaster / p:sldLayout inheritance).

That depth is a direction of travel, not a static checklist. PPT Master's north star is steady convergence with PowerPoint itself — integrating more native capabilities release after release to narrow the gap between what AI generates and what you would build by hand. The PowerPoint ↔ SVG Mapping Guide documents exact coverage feature by feature — SmartArt is a deliberate omission, not a gap.

In practice, it runs as a workflow ("skill") inside any agent-capable AI tool: ask in chat — "make a deck from this PDF" — and it handles analysis, design, and export locally into a natively editable .pptx. No coding required; you do three things — install Python, open an AI tool, drop in your material.

Generating a new deck from source documents is the main pipeline, but not the only route: PPT Master can also distill reusable brand, style, layout, or deck templates from your references, fill an existing .pptx with new content while preserving its design, or add native transitions, animations, and narration to a finished deck — each route with an explicit preservation contract. How to use each capability → Getting Started.

On top of that native depth, this form comes with three promises:

Transparent, predictable cost — free and open source; the only cost is your AI model usage, with no PPT subscription on top
Data stays local — apart from AI model calls and the search, image, and speech services you choose to enable, the entire pipeline runs on your machine
No platform lock-in — any agent-capable AI tool can drive it; Kimi, Gemini, GPT, Claude, and other models all work

Why you'd choose it, and where it isn't the right fit → Why PPT Master; the long-term capability boundaries behind these promises → Project Positioning.

[!IMPORTANT]

This is a tool, not a wishing well

harness + model = agent — PPT Master only owns the workflow; the model sets the ceiling. Recommended: Kimi K3.1 (or Gemini) with a large context window (~1M tokens) + AI image generation (gpt-image-2.6-sunburst or Google gemini-nano-banana-2.1); other models can run the pipeline, with a quality gap.

And don't expect a finished, perfect deck in one shot. The tool's value is taking most of the tedious work off your plate; the polishing that's left is yours — a natively editable deck exists precisely so you can keep working on it, not a flat image you can't touch. A cheap model won't match the recommended setup — that gap is the model's, not a PPT Master bug. The cheaper the model, the more there is to do; if results disappoint, upgrade the model first, then check your usage against Getting Started and the example projects.

High token use is this solution's trade-off, not a defect: the tool itself is free and open source, but model token costs are yours to cover, and this solution spends more tokens to deliver page-by-page design and native editability. Wanting excellent results without putting anything in is wishing, and that isn't achievable today; if this trade-off doesn't suit you, tools built on other approaches, or making the slides by hand, are perfectly good choices.

Built by Hugo He

I'm a finance professional (CPA · CPV · Consulting Engineer (Investment)) who regularly reviews and edits presentation decks. I wanted AI-generated slides to remain editable in PowerPoint, not flattened into images — so I built this.

Knowing how to use Python and AI agents will matter more and more, and this project is also meant to show how far you can go with just those two things. There's a learning curve if you're starting cold, but it's the curve worth climbing — making a deck is just the excuse; what I'm really pushing is Python and agents.

<a href="https://github.com/microsoft/ResearchStudio">ResearchStudio-<img src="https://raw.githubusercontent.com/ai-nuts/Storage/main/ResearchStudio/ResearchStudio-Reel/docs/figures/reel-wordmark.png" alt="Reel" height="16"></a>

A Microsoft open-source project I recently joined — from paper to talk video, poster, and blog, automating the last mile of research dissemination.

📦 Repo: microsoft/ResearchStudio · 📄 Paper: arXiv:2607.04438

<table align="center"> <tr> <td align="center" valign="middle" width="53%"> <a href="https://aka.ms/ResearchStudio"> <img src="https://raw.githubusercontent.com/ai-nuts/Storage/main/ResearchStudio/ResearchStudio-Reel/docs/figures/reel_demo.gif" width="100%" alt="ResearchStudio-Reel demo" /> </a> </td> <td align="center" valign="middle" width="47%"> <a href="https://aka.ms/ResearchStudio"> <img src="https://raw.githubusercontent.com/ai-nuts/Storage/main/ResearchStudio/ResearchStudio-Reel/docs/examples/latent_diffusion_landscape/poster.png" width="100%" alt="ResearchStudio-Reel generated poster" /> </a> </td> </tr> </table> <details> <summary>BibTeX — if you use ResearchStudio-Reel in your research</summary>

@article{xiao2026researchstudioreel,
  title   = {ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog},
  author  = {Lingao Xiao and Yalun Dai and Yangyu Huang and Qihao Zhao and Wenshan Wu and Hugo He and Ruishuo Chen and Jin Jiang and Qianli Ma and Jiahuan Zhang and Xin Zhang and Ying Xin and Yang Ou and Yan Xia and Scarlett Li and Longbo Huang and Zhipeng Zhang and Yang He and Yap Kim Hui and Yan Lu},
  journal = {arXiv preprint arXiv:2607.04438},
  year    = {2026},
  url     = {https://arxiv.org/abs/2607.04438}
}

</details>

Quick Start

1. Prerequisites

All you need to install is Python 3.10–3.14. Everything else comes with one line — pip install -r requirements.txt — after you download the project in Step 3.

<details> <summary>Windows — see the dedicated <a href="./docs/windows-installation.md">step-by-step guide</a> ⚠️</summary>

Windows requires a few extra steps (PATH setup, execution policy, etc.). We wrote a step-by-step guide specifically for Windows users:

📖 Windows Installation Guide — from zero to a working presentation in 10 minutes.

Quick version: download Python from python.org → check "Add to PATH" during install → done; dependencies are installed in Step 3.

</details> <details> <summary>macOS / Linux — install and go</summary>

# macOS
brew install python

# Ubuntu / Debian
sudo apt install python3 python3-pip

</details> <details> <summary>Edge-case fallback — 99% of users don't need this</summary>

Pandoc — only needed for legacy document formats: .doc, .odt, .rtf, .tex, .rst, .org, or .typ. .docx, .html, .epub, .ipynb are handled natively by Python — no pandoc required.

# macOS
brew install pandoc

# Ubuntu / Debian
sudo apt install pandoc

</details>

2. Pick an Agent

PPT Master runs in any tool with agent capability — read/write files, execute commands, and sustain multi-turn conversation.

Never used one of these? Don't worry — in this project they play exactly one role: an AI chat window that can read and write files. Pick any tool from the table, install it, and you'll only ever use its chat panel. No coding involved.

Author's pick: Claude Code — the environment this project is developed and tested on most thoroughly, as the CLI or the VS Code / JetBrains extension.

Type	Examples	Notes
IDE-native agent	• VS Code architecture (VS Code itself, plus forks & derivatives): Cursor, Antigravity, Trae, Codebuddy IDE, Windsurf, etc.<br>• Other architectures: Zed, etc.	Editor with a built-in agent
IDE plugin / extension	Claude Code (VS Code / JetBrains extension), GitHub Copilot, Cline, etc.	Installed inside hosts like VS Code or JetBrains
CLI agent	Claude Code CLI, Codex CLI, Gemini CLI, etc.	Runs in the terminal; suits scripting, remote, or server use

Model recommendation: for the best results, use Kimi K3.1 (or Gemini) to drive the pipeline, paired with AI image generation — gpt-image-2.6-sunburst (OpenAI) or gemini-nano-banana-2.1 (Google). Kimi Code, the project sponsor, is a great pick for pay-as-you-go access.

🔑 Want to use Gemini / GPT / Claude but don't have access yet? Project sponsors PackyCode, APIKEY.FAN, RunAPI and ModelGo offer pay-as-you-go access to Gemini, GPT, Claude and more — no subscription required, with exclusive discounts for our users (details at the top of this page).

🔀 Juggling several providers? Once you hold keys from more than one of them, cc-switch — a cross-platform desktop app — lets you one-click switch API providers for Claude Code, Codex, Gemini CLI and more, no manual config editing.

3. Set Up

Option A — Git clone (recommended; requires Git installed): the preferred path, since a clone can pull the latest version at any time.

git clone https://github.com/hugohe3/ppt-master.git
cd ppt-master

Then install dependencies:

pip install -r requirements.txt

Option B — Download ZIP (no Git required; best for a quick trial): click Code → Download ZIP on the GitHub page, then unzip, and install dependencies with pip install -r requirements.txt. A ZIP has no Git history, so it can't git pull — see Updating Later. If that download is too large or fails, grab the skill-only package ppt-master-skill-*.zip (~23 MB, fully functional but without the bundled example decks) from the Releases page instead.

Updating Later

Git clone installs:

python3 skills/ppt-master/scripts/update_repo.py

The script pulls the latest version and syncs Python dependencies when requirements.txt changes.

Download ZIP installs:

ZIP folders do not include Git history, so they cannot run git pull. To update, download the latest ZIP, unzip it into a new folder, copy your old .env and projects/ folder into the new folder, then run:

pip install -r requirements.txt

Option C — Skill marketplace: the repo ships .claude-plugin/marketplace.json, so it can be installed through the Claude Code plugin marketplace ecosystem:
# Cross-agent CLI (Claude Code, Cursor, Codex, etc.)
npx skills add hugohe3/ppt-master

# Or inside Claude Code
/plugin marketplace add hugohe3/ppt-master
/plugin install ppt-master@ppt-master
Both install paths above only fetch the skill files (not the full repo); you still need to pip install -r requirements.txt from the installed location for the post-processing scripts to run.

4. Create

First, open the project folder in your agent: the goal is to point the AI at the ppt-master directory you unzipped / cloned in the previous step. In an IDE-type tool, use File → Open Folder — the AI chat panel is usually in the sidebar; in a CLI agent, cd ppt-master first, then launch it. Everything from here on happens in the chat.

Provide source materials (recommended): Place your PDF, DOCX, images, or other files in the projects/ directory, then tell the AI chat panel which files to use. The quickest way to get the path: right-click the file in your file manager or IDE sidebar → Copy Path (or Copy Relative Path) and paste it directly into the chat.

You: Please create a PPT from projects/q3-report/sources/report.pdf

Paste content directly: You can also paste text content straight into the chat window and the AI will generate a PPT from it.

You: Please turn the following into a PPT: [paste your content here...]

By default—unless you explicitly request quick generation—the AI first confirms the design spec:

AI:  Sure. Let's confirm the design spec:
     [Template] B) Free design
     [Format]   PPT 16:9
     [Pages]    8-10 pages
     ...

The AI handles everything — content analysis, visual design, SVG generation, and PPTX export.

Quick generation (skip the confirmation round trip): say so explicitly and the AI goes straight to authoring and export.

You: Quickly generate a 5-page deck from projects/q3-report/sources/report.pdf — no need to confirm with me

Whatever you state explicitly is followed; whatever you leave unspecified the agent decides on its own instead of asking. It still converts sources, fills factual gaps, applies the shared visual baseline, and uses images/icons/native shapes/charts/tables/PowerPoint-native inline or block formulas as needed — it drops interaction and durable planning, not presentation capability. It is one-pass and non-resumable, and there is no svg_final/ preview. Full guide → Quick mode.

Output: the deck lands in exports/<name>_<timestamp>.pptx as natively editable DrawingML; the default flow also writes self-contained page previews to svg_final/. Charts and tables ship as editable shapes by default; pass --native-charts-and-tables for data-backed PowerPoint Chart / Table objects with Edit Data, saved as a separate _native_charts_tables.pptx. Formulas compile to editable OMML for PowerPoint 2010+. Backups, notes, animation and narration switches, and the non-PowerPoint boundaries → FAQ.

Already have a .pptx you want to reuse? Give the AI the deck and material and ask it to "fill this deck with the new content" — Edit Native PPTX keeps the design and unchanged pages byte-for-byte, edits chosen pages, supports selection/reordering, and can add notes or narration. See the FAQ and workflow.

Something went wrong? If the AI loses context, ask it to read skills/ppt-master/SKILL.md; for everything else, check the FAQ — it covers model selection, layout issues, export problems, and more. Continuously updated from real user reports.

5. Image Acquisition (Optional)

Two paths for non-user images, mixable per image in the same deck:

A) AI generation — use the agent host's native image tool when available, or image_gen.py with IMAGE_BACKEND plus the provider's *_API_KEY. Host-native generation needs no separate provider image API key; ask the agent to use its own image tool. Run python3 skills/ppt-master/scripts/image_gen.py --list-backends for the configured-provider path. gpt-image-2.6-sunburst is the current OpenAI default.

B) Web image search — image_search.py. Zero-config works; configure PEXELS_API_KEY / PIXABAY_API_KEY (both free) for consistently higher-quality results:

Without keys, search uses Openverse / Wikimedia Commons only — useful as a fallback, but image quality can be uneven because many results are ordinary user uploads
With keys, the default provider chain also appends Pexels / Pixabay, which materially improves modern stock photography, people, workplace, lifestyle, and illustration coverage
Licensing is handled automatically: CC0, Public Domain, Pexels / Pixabay no-attribution licenses, CC BY, and CC BY-SA are all considered together, and Executor adds a small inline credit whenever the selected image requires attribution. Use --strict-no-attribution only when a slide cannot tolerate any credit line
For high-impact covers, product shots, portraits, and branded scenes, prefer this order: user-provided high-resolution assets / AI generation > web search with Pexels / Pixabay keys > zero-config web search

The API keys above all live in .env. Clone installs can use cp .env.example .env; skill marketplace installs should use a persistent user config:

mkdir -p ~/.ppt-master
cp /path/to/installed/ppt-master/.env.example ~/.ppt-master/.env

PPT Master reads the current process environment first, then the first .env found in this order: current working directory, skill directory (e.g. ~/.agents/skills/ppt-master/.env), clone repo root, ~/.ppt-master/.env.

Full reference: image-generator.md (AI) · image-searcher.md (web).

Documentation

	Document	Description
📘	Getting Started	First deck in 3 steps, plus how to use templates, live preview, animations, narration, voice cloning (new users start here)
🆚	Why PPT Master	Why choose it, and where it's not the right fit
🧭	Project Positioning	Long-term positioning, product promises, and capability boundaries
🪟	Windows Installation	Step-by-step setup guide for Windows users
📖	SKILL.md	Core workflow and rules
📐	Canvas Formats	PPT 16:9, Xiaohongshu, WeChat, and 10+ formats
🛠️	Scripts & Tools	All scripts and commands
💼	Examples	All example projects
🏗️	Technical Design	Architecture, design philosophy, why SVG
❓	FAQ	Model selection, cost, layout troubleshooting, custom templates

Full documentation index → docs/

Contributing

See CONTRIBUTING.md for how to get involved.

License

MIT

Acknowledgments

SVG Repo · Tabler Icons · Simple Icons · Phosphor Icons · Robin Williams (CRAP principles)

See third-party icon notices for pinned versions, licenses, attribution, compatibility overlays, and trademark boundaries.

The optional PDF converter depends on PyMuPDF, which is licensed under AGPL-3.0 rather than MIT; it is only needed for PDF sources. See conversion.md before redistributing a bundle that includes it.

Related Tools

cc-switch — one-click switching of API providers across Claude Code / Codex / Gemini CLI and more.

Contact & Collaboration

Looking to collaborate, integrate PPT Master into your workflow, or just have questions?

💬 Questions & sharing — GitHub Discussions
🐛 Bug reports & feature requests — GitHub Issues

Star History

Sponsors & Support

PPT Master is currently built and maintained primarily by me. Every new template, bug fix, and documentation update takes ongoing resources — currently shared by the sponsors and individual supporters below.

Corporate sponsors

Want to appear here? → — placements, audience and rates.

Individual support

If PPT Master has been helpful to you, individual support of any amount helps keep the project moving and free.

Made with ❤️ by Hugo He — if this project helps you, please give it a ⭐ and consider sponsoring.

Official distribution: <a href="https://github.com/hugohe3/ppt-master">GitHub</a> (primary) · <a href="https://atomgit.com/hugohe3/ppt-master">AtomGit</a> (mirror). Redistributions on other platforms are unofficial. MIT licensed — attribution required.

⬆ Back to Top

Ppt Master alternatives

View more →

Similar ai agents in Productivity & Workflow, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.

Name	Stars	Licence	Last updated	Scan
Ppt Master (this page) hugohe3	72k	MIT	Oct 30, 2026	Scanned, no flagged issues
Paperclip paperclipai	110k	MIT	Nov 1, 2026	Scanned, no flagged issues
Llama Index run-llama	53k	MIT	Oct 26, 2026	Scanned, see report
Nanobot HKUDS	50k	MIT	Oct 31, 2026	Scanned, no flagged issues
Sim simstudioai	30k	Apache-2.0	Nov 1, 2026	Scanned, see report
Activepieces activepieces	25k	None found	Nov 1, 2026	Not scanned yet