# huohua325/Memslides

A hierarchical memory framework for personalized presentation agents. Try it at memslides.com.

Repository: https://github.com/huohua325/Memslides
Canonical: https://ross.abutalabs.com/products/memslides
Homepage: https://arxiv.org/abs/2606.17162
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, deck, llm-tools, slides
Last push: 2026-08-29T16:05:10+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 100, release rhythm 57, longevity 8
- inputs: {"age_days": 122, "days_push": 4, "days_rel": 79, "gap_med": null, "n_releases_24m": 1}
- flags: prerelease_only, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1054, forks 32 (observed 2026-09-01T02:14:02.929947+00:00)

## What it is
MemSlides is a hierarchical memory-driven agent framework for generating and revising personalized slide decks. It separates long-term memory (user profile memory and tool memory) from working memory, and applies scoped slide-local revision so edits touch only the smallest affected region instead of regenerating the whole deck.

## Use cases
- Generate a personalized presentation deck from a prompt and stored user preferences
- Revise individual slides across multiple turns without regenerating the full deck
- Persist user intent and style preferences across separate presentation tasks
- Reuse stored tool execution experience for reliable localized slide edits
- Run a research-backed presentation agent locally via Docker or try it on the hosted demo

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, prompt-engineering
- domain: -
- platform: python
- tags: slides, presentation, memory, personalization, llm-agent, llm-tools, nodejs, docker, web

## Member repositories
- huohua325/Memslides (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-09-01T02:14:02.929947+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 2026-08-30T06:58:47.357941+00:00, confidence not recorded.
  - readme: https://github.com/huohua325/Memslides (fetched 2026-09-01T02:14:02.929947+00:00, sha bb313ed3c87b)
  - homepage: https://arxiv.org/abs/2606.17162 (fetched 2026-08-29T13:00:38.750531+00:00, sha 79e4e5b0cf98)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T13:00:38.754352+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T13:00:38.759285+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T13:00:38.761231+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T13:00:38.757082+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.