mcp-server

LycheeMem: Lightweight Memory

Get long-term memory for LLM agents with LycheeMem, used by developers.
1,167 stars16 forksPythonGuide quality 8/10Updated 7/17/2026100% 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

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
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
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/lycheemem && curl -fsSL https://workflowstacks.com/api/skills/lycheemem/claude-skill -o ~/.claude/skills/lycheemem/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How LycheeMem: Lightweight Memory works
Codeflow
Free to inspect

LycheeMem: Lightweight Memory is a large Python project (~29k lines across 123 code files, plus 1 test files). Setup is light: installs like a normal app — add your API keys. Reading the code is optional. Last commit a month ago, Apache-2.0 license, has a test suite.

Size
Large codebase
~29k lines · 123 code files · ~4 h to skim
Setup
One-command install
Installs like a normal app — add your API keys. Reading the code is optional.
Runs on
Python
Needs API keys (.env)
Python 82%TypeScript 14%CSS 5%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    main.py
    Where the program starts running
  3. 3
    pyproject.toml
    Dependencies and the commands it exposes
  4. 4
    .env.example
    The API keys and settings you must provide
  5. 5
    src/__init__.py
    Inside src/ — the main logic begins here
What's in each folder
src/Core code — the actual logic82 files
examples/Examples you can copy1 files
web-demo/Folder26 files
vision/Folder11 files
hermes-plugin/Folder10 files
openclaw-plugin/Folder10 files
claude-plugin/Folder9 files
assets/Images & static assets5 files
READMEHas testsDocumentedNo CIExamples includedApache-2.0 licenseUpdated 1 mo ago
Quick Actions
Details
Creator
LycheeMem
Language
Python
Category
mcp-server
Published
3/23/2026

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.