# icip-cas/PPTAgent

An Agentic Framework for Reflective PowerPoint Generation

Repository: https://github.com/icip-cas/PPTAgent
Canonical: https://ross.abutalabs.com/products/pptagent
Homepage: https://arxiv.org/abs/2501.03936
Language: Python
License: MIT
License Family: permissive
Topics: agent, llm, presentation, slide, agentic-ai, mcp, openclaw
Last push: 2026-08-24T20:52:49+00:00

## Health v2 (maintenance only)
Score: 70/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 49, longevity 43
- inputs: {"age_days": 607, "days_push": 9, "days_rel": 260, "gap_med": 63, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4954, forks 579 (observed 2026-08-28T04:09:03.775233+00:00)

## What it is
PPTAgent is an agentic Python framework that automatically generates PowerPoint presentations from documents using a two-stage, edit-based approach inspired by human workflows. It analyzes reference presentations to extract slide schemas, iteratively generates editing actions, and includes PPTEval for evaluating content, design, and coherence.

## Use cases
- generate a powerpoint presentation from a pdf or document
- automatically create slides from my research paper
- convert a report into a pptx deck with ai
- build presentations that match an existing slide template
- evaluate the quality of generated slides
- automate slide deck creation with an llm agent

## When to choose
- you need to turn long documents into structured, visually coherent slide decks automatically
- you want presentations that follow the layout and style of reference decks
- you need programmatic, agent-driven pptx generation with quality evaluation

## When to avoid
- you only need simple text-to-slide bullet points without design or structure concerns
- you require a polished GUI presentation editor rather than a programmatic framework
- you cannot deploy or access an LLM backend, which the framework depends on

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, prompt-engineering, mcp, pdf, nlp
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cross-platform, cli
- tags: powerpoint, presentation-generation, pptx, slides, document-to-slides, agentic-ai, pptagent, ppteval, ai-agents, natural-language-processing, automation

## Member repositories
- icip-cas/PPTAgent (main) score 70

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:03.775233+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:17:50.741060+00:00, confidence not recorded.
  - readme: https://github.com/icip-cas/PPTAgent (fetched 2026-08-28T04:09:03.775233+00:00, sha a0d6db349cdb)
  - homepage: https://arxiv.org/abs/2501.03936 (fetched 2026-08-29T08:59:18.105839+00:00, sha dec9f941fa34)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T08:59:18.114917+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T08:59:18.118237+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T08:59:18.120167+00:00, sha a1f16f915a9a)
  - registry_pypi: https://pypi.org/pypi/pptagent/json (fetched 2026-08-29T08:59:18.121853+00:00, sha 32fb58b902af)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T08:59:18.116569+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.