Skip to main content
Glama
Wakanlolz

memory-decay

by Wakanlolz
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MEMORY_STORAGE_PATHNoOptional environment variable to set the directory where the vector database and journal file are stored. Defaults to ./data relative to the working directory../data

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
store_memoryA
Stores a memory with a specific category (episodic, semantic, procedural).
- episodic: Short-term context (logs, current tasks).
- semantic: Facts, preferences, user identity.
- procedural: Code patterns, logic, workflows.
recall_memoryA

Retrieves memories based on semantic relevance and decay. Successfully recalled memories receive a 'Hebbian boost', refreshing their strength.

verify_historyA

Bypasses decay to search the immutable Archive. Use for audit or when recall fails.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Wakanlolz/PyMemoryDecayMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server