codex-slides
🎨 Open-source AI slide studio inside Codex: image-native decks, every slide a full visual canvas. ⚡ 10+ high-quality slides in ~4–5 minutes — Fast mode renders every page in parallel. 🔍 Watch the whole chain live: research → outline → style → render → edit → present → export PDF/PPTX. 🖥️ Browser-fir
Codex Slides is an open-source MCP server and Codex plugin that transforms AI coding agents into presentation studios, generating image-native slide decks from prompts, repositories, or files. It exposes 38 typed MCP tools covering the complete workflow—research, outline, styling, rendering, editing, presenting, and exporting to PPTX/PDF—while keeping every step visible in a browser-first interface. Ships with 118 ready-made visual systems (45 curated templates + 73 community styles) and 24 guided scenarios, rendering 10+ slides in ~4–5 minutes via parallel Fast mode. Runs on existing Codex authentication with zero separate API keys, storing all projects locally on disk.
Key Features
Use Cases
- 01Generate market reports, investor pitch decks, and product keynotes from prompts or repository context
- 02Transform documents, spreadsheets, transcripts, and whiteboards into styled presentation decks
- 03Create data visualization dashboards with maps, charts, and KPI tiles from CSV/JSON datasets
- 04Build training modules, research readouts, and competitive analyses with guided scenario workflows
- 05Apply brand systems and restyle entire decks while preserving content and structure
- 06Collaborate on presentations with live browser synchronization and shareable presenter mode
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
codex-slides — FAQ
What is Codex Slides?+
Codex Slides is an open-source MCP server and Codex plugin that enables AI coding agents to create, edit, and export presentation decks through a browser-first workflow. It treats presentations as durable, inspectable projects with every step—research, outline, styling, rendering, editing—visible and steerable rather than hidden in a black box.
How do I install Codex Slides in Codex?+
Run 'codex plugin marketplace add nexu-io/codex-slides' then 'codex plugin add codex-slides@codex-slides' and restart Codex or the ChatGPT desktop app. You can also clone the repository and add it from a local checkout using 'codex plugin marketplace add' with the absolute path.
Which AI clients does Codex Slides work with?+
Codex Slides is designed for OpenAI's Codex coding agent and ChatGPT desktop app with plugin support. It exposes both a portable Skill and 38 typed MCP tools, with roadmap plans for broader bring-your-own-agent support beyond Codex.
Do I need API keys or separate accounts?+
No separate API keys are required. Codex Slides runs on your existing 'codex login' authentication and uses the same Codex environment for text generation, web research, and image generation. All projects are stored locally on disk.
Is Codex Slides free and open source?+
Yes, Codex Slides source code is available under the MIT License. Community style previews and adapted prompt references retain upstream terms documented in the repository. No additional licensing or subscription fees are required.
What prerequisites do I need to run Codex Slides?+
You need Codex with plugin support, Node.js 20 or newer, a ChatGPT account authenticated with 'codex login', and Git. The repository includes both web and Electron desktop builds for macOS, Windows, and Linux.
How do I install codex-slides?+
Open the source repository on GitHub and follow its README. codex-slides is a mcp server — MCP Agents Market links you directly to the official repo.
Is codex-slides free?+
codex-slides is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.