#1313th of 14 in Desktop AI apps

presenton

Generates editable PPTX and PDF slide decks from prompts or documents

Stars
11.2k
License
Apache-2.0
Last commit
Oct 2026
Last release
Sep 2026
Language
TypeScript
Stars, last 29 weeks+6,818
31 Mar 2026: 4,429 stars7 Apr 2026: 4,489 stars14 Apr 2026: 4,597 stars21 Apr 2026: 4,676 stars28 Apr 2026: 4,747 stars5 May 2026: 4,804 stars12 May 2026: 4,890 stars19 May 2026: 4,977 stars26 May 2026: 7,029 stars2 Jun 2026: 7,677 stars9 Jun 2026: 7,943 stars16 Jun 2026: 8,257 stars23 Jun 2026: 8,393 stars30 Jun 2026: 8,506 stars7 Jul 2026: 8,871 stars14 Jul 2026: 8,968 stars21 Jul 2026: 9,045 stars28 Jul 2026: 9,144 stars4 Aug 2026: 9,277 stars11 Aug 2026: 9,411 stars18 Aug 2026: 9,637 stars25 Aug 2026: 9,802 stars1 Sept 2026: 9,924 stars8 Sept 2026: 10,092 stars15 Sept 2026: 10,191 stars22 Sept 2026: 10,675 stars29 Sept 2026: 10,822 stars6 Oct 2026: 10,960 stars13 Oct 2026: 11,092 stars20 Oct 2026: 11,247 stars

4,429 on 31 Mar 202611,247 on 20 Oct 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

Presenton is a self-hosted presentation generator that builds slides from a prompt, an uploaded document, or a PowerPoint-derived template, and exports editable PPTX or PDF. It runs as a Docker web app or an Electron desktop app, exposes a generation API and a built-in MCP server, and connects to OpenAI, Anthropic, Gemini, Ollama, LM Studio, Bedrock and other providers.

Who it is for: Teams wanting a self-hosted alternative to Gamma or Canva for slide decks

Strengths

  • Exports fully editable PPTX as well as PDF
  • Many text LLM providers, including local Ollama and LM Studio, plus any OpenAI-compatible endpoint
  • Includes a generation API, a built-in MCP server and multi-user workspaces with an admin panel
  • Custom templates in HTML and Tailwind, or generated from an existing PowerPoint file

Weaknesses

  • SSO, SCIM, audit logs and Helm charts are only in the Enterprise edition
  • Community template gallery calls a cloud service by default; air-gapped setups must disable it
  • README gives no RAM, VRAM or model-size guidance for local models
  • README documents only a source build for the desktop app; installers are on the website

What it needs

  • GPU optional
  • Docker + Compose
  • Needs Docker, or Node.js, Python 3.11 and uv for Electron, LLM provider or API key
  • Models: OpenAI, Anthropic, Google Gemini, Vertex AI, Azure OpenAI
  • port 5001

Also in Desktop AI apps

See all 14
Also in Desktop AI apps
RankProjectScore
1prompt-optimizerPrompt rewriting and testing tool for web, desktop, Chrome and MCP Live demo ↗ (opens in a new tab)38.8k starscustom license80 out of 100
2cherry-studioCross-platform desktop chat client for many cloud and local LLM providers Live demo ↗ (opens in a new tab)52.8k starsAGPL-3.079 out of 100
3deep-live-camReal-time webcam face swap from a single source image97.2k starsAGPL-3.076 out of 100
#4dsh-desktopNative Windows and macOS desktop client for DeepSeek Harness32.1k starsMIT73 out of 100
#5screenpipeRecords screen and audio locally, makes it searchable for you and your agents22k starscustom license73 out of 100