mcp-server

LycheeMem: Lightweight Memory

Name: LycheeMem: Lightweight Memory
Author: LycheeMem

Get long-term memory for LLM agents with LycheeMem, used by developers with 1.1k+ GitHub stars. For founders building AI-powered projects.

1,112 stars15 forksPythonQuality 8/10Updated 7/7/2026100% free · open source

What it does

LycheeMem provides long-term memory for LLM agents, enabling them to retain information over extended periods and recall it when needed

Install / run

pip install lycheemem

When to use it

•When building conversational AI models that require remembering context or user interactions
•When developing AI-powered chatbots that need to recall previous conversations or user data
•When creating AI systems that require retaining knowledge or information over time

Quick start

1Clone the LycheeMem repository using `git clone https://github.com/LycheeMem/LycheeMem.git`
2Navigate to the repository directory using `cd LycheeMem`
3Install the required dependencies using `pip install -r requirements.txt`
4Run the example script using `python examples/example.py` to test LycheeMem's functionality
5Modify the `config.json` file to configure LycheeMem's memory settings and thresholds

Ready-to-paste prompt

python examples/example.py --model-name 'my-llm-model' --memory-size 1024 --threshold 0.5

Heads up: Make sure to configure the `memory_size` parameter in the `config.json` file according to your available RAM, as LycheeMem's memory usage can be substantial

Saves to your device