bowen-upenn/PersonaMem-v2

PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory

24
/ 100
Experimental

This project helps AI developers and researchers evaluate how well large language models (LLMs) can understand and adapt to individual user preferences from long conversations. It takes simulated chat histories where user preferences are implicitly revealed and outputs performance metrics, showing how effectively an LLM can provide personalized responses. It's designed for those building and testing personalized AI agents or systems.

Use this if you are a developer or researcher focused on enhancing LLM personalization capabilities and need a robust benchmark to test how well models infer user preferences from extensive, implicit conversational cues.

Not ideal if you are looking for an off-the-shelf personalized AI agent or a tool for directly interacting with users, as this is primarily an evaluation benchmark and training framework.

LLM personalization AI agent development conversational AI user profiling AI model evaluation
No License No Package No Dependents
Maintenance 13 / 25
Adoption 4 / 25
Maturity 7 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Python

License

Last pushed

Mar 18, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/bowen-upenn/PersonaMem-v2"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.