HomeProjectsArticlesPK BoardAbout
Explore Projects

Presenton

Active
GitHub TypeScript Apache-2.0

Description

An open-source AI presentation generator and API that creates professional slides from text, as an alternative to Gamma, Beautiful AI and Decktopus.

Key Features

  • Open-source AI presentation generator creating professional slides from text as alternative to Gamma and Beautiful AI
  • Self-hosted via Docker or desktop app (Mac, Windows, Linux) with full data privacy control
  • Multi-provider support: OpenAI, Gemini, Vertex AI, Azure OpenAI, Anthropic, Ollama, and custom models
  • Fully editable PPTX export with custom HTML/Tailwind CSS templates and themes
  • Built-in MCP server for generating presentations via Model Context Protocol
  • Sign in with ChatGPT account for instant access without separate API keys

Use Cases

💡 Generating professional business presentations from text prompts or uploaded documents
💡 Creating AI-powered slide decks with custom branding and design templates
💡 Building presentation generation APIs for team or organizational use
💡 Rapid prototyping of pitch decks and reports using AI with full offline capability

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (10.0k stars)
  • • Permissive open-source license (Apache-2.0)
  • • Responsive to issues, low backlog

Tags

memory typescript agent automation tools

Categories

🧩 Agent Memory

Quick Start

Docker: docker run -it --name presenton -p 5000:80 ghcr.io/presenton/presenton:latest. Open http://localhost:5000. Or download the desktop app from presenton.ai/download.
Visit GitHub Visit Website

Related Projects

OpenMemory

4.5k · TypeScript
Active A+

Local persistent memory store for LLM applications including Claude Desktop, GitHub Copilot, Codex, and more. Provides durable context memory capabilities for AI agents.

memorytypescriptagent +1
  • · Multi-sector cognitive memory: episodic, semantic, procedural, emotional, reflective
  • · Temporal knowledge graph with valid_from/valid_to for time-aware recall
  • · Self-hosted local-first storage via SQLite or Postgres, no vendor lock-in
View on GitHub

WiseFlow

8.5k · Python
Active A+

A 24/7 online AI agent team that automates information collection, data analysis and content generation for continuous operations.

memorytypescriptagent +2
  • · Multi-Agent system based on OpenClaw with built-in crews for business development, social media operations, design, and more
  • · 24/7 online automated operations for information collection, data analysis, and content generation
  • · WeChat onboarding via conversation — no config files needed, guided setup through chat
View full details → View on GitHub

Claude Mem

93.0k · JavaScript
Active A+

A Claude Code plugin that automatically captures coding session context, compresses it with AI, and injects relevant context back into future sessions for persistent memory.

codingmemoryagent +2
  • · Cross-session persistent memory - Automatically captures tool observations and generates semantic summaries, injecting relevant context into new sessions
  • · Progressive disclosure - Layered memory retrieval with token cost visibility for precise control over injected context volume
  • · Skill-based search - Query project history via mem-search skill with semantic project context retrieval
View full details → View on GitHub