simplemindedbot/stm-research
If you are the rightful owner of stm-research and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
The STM Research project provides a Model Context Protocol (MCP) server that simulates human-like memory dynamics for AI assistants, using a temporal decay algorithm inspired by cognitive science.
Tools
Functions exposed to the LLM to take actions
save_memory
Save new memory with tags and entities.
search_memory
Search memories with filters and scoring.
touch_memory
Reinforce memory by boosting its strength.
gc
Garbage collect low-scoring memories.
promote_memory
Move memory to long-term storage.
cluster_memories
Find similar memories.
consolidate_memories
Merge duplicate memories using LLM.
read_graph
Retrieve the entire knowledge graph.
open_memories
Retrieve specific memories.
create_relation
Link memories explicitly.
Prompts
Interactive templates invoked by user choice
No prompts
Resources
Contextual data attached and managed by the client