presenton/presenton

Project overview

For teams facing lock-in and forced subscriptions with SaaS presentation tools, presenton offers a self-hosted alternative with editable PPTX export and a built-in MCP server for generating presentations programmatically.

Project type

AI Agent

Use cases

Documents & Office

Deployment

Refer to project documentation

License

Apache-2.0

Best for

• Users who want to avoid SaaS presentation tool lock-in and subscriptions and prefer a self-hosted, open-source option with editable PPTX export.
• Users who want to choose their own LLM provider, including local models via Ollama or LM Studio.

Key capabilities

• Generates presentations from a prompt or an uploaded document.
• Exports fully editable PowerPoint (.pptx) and PDF presentations.
• Works with Ollama, LM Studio, OpenAI, Gemini, Vertex AI, Azure OpenAI, Amazon Bedrock, and other OpenAI-compatible providers.

Getting started

• Run docker run -it --name presenton -p 5001:80 -v "./app_data:/app_data" ghcr.io/presenton/presenton:latest, then open http://localhost:5001 in the browser and follow the account setup screen to create the primary administrator. No coding is required.

Evidence and sources

• GitHub project description: Open-Source AI Presentation Generator and API (Gamma, Canva, Beautiful AI, Decktopus, Presentations AI Alternative)
• README: Works with Ollama, LM Studio, OpenAI, Gemini, Vertex AI, Azure OpenAI, Amazon Bedrock, Fireworks, Together AI, Anthropic, or any other OpenAI compatible providers
• README: Create presentations from a prompt, an uploaded document, or your own PowerPoint design.
• README: use Presenton to generate fully editable PowerPoint (`.pptx`) or PDF presentations from a prompt or document.
• README: docker run -it --name presenton -p 5001:80 -v "./app_data:/app_data" ghcr.io/presenton/presenton:latest

Source updated at: 2026-10-18T02:59:24Z

Open original GitHub project