Presenton presenton/presenton

AI presentation generator with built-in templates, drag-edit slides and editable PPTX/PDF export; desktop app or self-hosted Docker, BYO model.

Creator kit + Compare GitHub ↗ Install guide (official) ↗

Presenton at a glance

Checked 15 Oct 2026

Presenton generates slide decks from a prompt, an uploaded document or your own PowerPoint design, then lets you edit and export editable PPTX or PDF. It runs as a desktop app (macOS, Windows, Linux) or a Docker container, and works with Ollama or LM Studio for fully local text models or with paid APIs. Apache-2.0. It only does presentations: no social graphics, print or whiteboards. No minimum hardware documented; local models can use an NVIDIA GPU.

Cite this pageRepoQuarry. “Presenton.” Checked 15 Oct 2026. https://repoquarry.dev/projects/presenton

How much of Canva does it replace?

1 of 5 jobs. AI-generated, editable decks from templates; presentations only.

Template-based social and marketing graphics Not covered

Designed presentations and slide decks Partial replacement

Brand kits (shared colours Not covered

Online whiteboards Not covered

Print designs (posters Not covered

For template-based social and marketing graphics, brand kits (shared colours, online whiteboards, print designs (posters, see other Canva alternatives. You may also need to build an interface, an API server and hosting yourself.

Facts, with sources

Every answer links to where we found it. We read the documentation; we did not install it.

Report a correction

QuestionAnswerSourceChecked

Runs on my machine? Yes, desktop app or self-hosted Docker; can use local models through Ollama Create AI-powered presentations using your own model provider (BYOK) or run everything locally on your own machine for full control and data privacy. github.com · presenton#readme ↗ 1d ago

Code licence Apache-2.0 Fully open-source (Apache 2.0) github.com · presenton#readme ↗ 1d ago

Model weights licence No bundled weights; uses the model you connect, under that model's licence github.com · presenton#readme ↗ 1d ago

Commercial use Yes, Apache-2.0 (check the licence of any model you connect) github.com · LICENSE ↗ 1d ago

Paid services needed? None required with Ollama; optional paid LLM and image APIs Works with Ollama, LM Studio, OpenAI, Gemini, Vertex AI, Azure OpenAI, Amazon Bedrock, Fireworks, Together AI, Anthropic, or any other OpenAI compatible providers github.com · presenton#readme ↗ 1d ago

Hardware No minimums documented; NVIDIA GPU optional for local Ollama models in Docker To use GPU acceleration with Ollama models, you need to install and configure the NVIDIA Container Toolkit. github.com · presenton#readme ↗ 1d ago

Operating systems Desktop app for macOS (Apple Silicon and Intel), Windows x64, Linux x64 (.deb); Docker Or Download [Desktop App](https://presenton.ai/download) (Mac, Windows & Linux) github.com · presenton#readme ↗ 1d ago

Setup effort Easy; desktop installer, or one docker run command docker run -it --name presenton -p 5001:80 -v "./app_data:/app_data" ghcr.io/presenton/presenton:latest github.com · presenton#readme ↗ 1d ago