zjunlp/MemP

MemP: Exploring Agent Procedural Memory

29
/ 100
Experimental

This project helps developers improve the ability of AI agents to perform complex, multi-step tasks more reliably and efficiently. It takes existing agent interaction data or allows agents to learn through experience, and outputs refined instructions and task abstractions. AI engineers and researchers working with large language model-based agents would use this.

Use this if you are building AI agents with Large Language Models and want them to learn from past experiences to perform future tasks better, or if you need to transfer learned procedures between different agent models.

Not ideal if you are looking for a ready-to-use application and are not comfortable with programming and setting up AI development environments.

AI agent development Large Language Models AI workflow automation Machine learning engineering Autonomous systems
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 13 / 25
Community 0 / 25

How are scores calculated?

Stars

16

Forks

Language

Python

License

MIT

Last pushed

Jan 30, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/zjunlp/MemP"

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