presenton / presenton

2025-05-10 · Source: Github Trending: All languages · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Cloud Computing & IT Infrastructure · Depth: Intermediate, long

Summary

Presenton is an open-source AI presentation generator and API, available as a self-hosted web application via Docker or a native desktop app for macOS, Windows, and Linux. It supports a wide array of large language model (LLM) providers, including OpenAI, Google Gemini, Vertex AI, Azure OpenAI, Amazon Bedrock, Fireworks, Together AI, Anthropic, LM Studio, and Ollama, alongside custom model integration. Key features include fully editable PPTX export, custom template creation using HTML and Tailwind CSS, AI-driven template generation from existing PowerPoint files, and flexible presentation generation from text prompts or uploaded documents. The platform is Apache 2.0 licensed, offers an API for programmatic generation, and supports GPU acceleration for local Ollama models. It also provides a browser-based "Cloud" option.

Key takeaway

For AI Engineers or DevOps teams building internal content generation tools, Presenton offers a robust, self-hosted alternative to SaaS presentation generators. You gain full control over your LLM providers, data privacy, and customization options, avoiding vendor lock-in. Consider deploying it via Docker with GPU support to integrate AI-powered presentation creation directly into your workflows, especially for sensitive data or custom model requirements.

Key insights

Presenton offers a self-hosted, open-source AI presentation solution with extensive model and data control.

Principles

• Full control over models and data.
• Avoids SaaS lock-in and forced subscriptions.
• Open-source for transparency and modification.

Method

Users can generate presentations via a POST request to "/api/v1/ppt/presentation/generate", providing content, slide count, language, and template, with optional web search and file integration.

In practice

• Deploy Presenton via Docker with GPU support.
• Integrate custom LLM endpoints for generation.
• Automate report generation from CSV via API.

Topics

• AI Presentation Generation
• Open-Source AI
• Self-Hosted Deployment
• LLM Integration
• Docker
• API Automation

Code references

• presenton/presenton
• orgs/presenton

Best for: Machine Learning Engineer, AI Engineer, Software Engineer, DevOps Engineer

Related on AIssential

• This Lamp Folds Your Laundry — Live user data and dedicated infrastructure are crucial for production-ready LLMs.
• Self-Hosted AI: A Complete Roadmap for Beginners — Build a private AI automation hub using Docker, Ollama, and n8n for local, cloud-independent workflows.
• Why Can't Anyone Answer Questions About the Business? — Garrett Galow, WorkOS — WorkOS's Studio uses an LLM-powered agent to answer internal business questions and build reusable data widgets from diverse data sources.
• DIY dev tools: How this engineer created “Flowy” to visualize his plans and accelerate coding — Custom AI-native dev tools enhance planning and coding efficiency by enabling visual iteration and model-to-model evaluation.
• The Localhost Ego Trip — Over-reliance on self-hosting one LLM can hinder optimal architecture and obscure true engineering challenges.
• Architecting Modern AI Systems: Platforms, Agents, and Integration — Open-source models and sovereign AI platforms offer cost control, data residency, and output flexibility over closed-source APIs.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Github Trending: All languages.