aiming-lab/SimpleMem

[ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal

About the project

SimpleMem is a long-term memory system for large-language-model agents that compresses, stores, and retrieves text and multimodal memories using semantic search. It is used with AI platforms that support MCP or Python to give agents persistent memory across text, images, audio, and video. Its catalogue skill supports workflows for using SimpleMem.

3.8kStars on the repository

1Mods indexed here, across every type

2mo agoLast push, which is what freshness is scored on

MITLicence, which decides whether bodies are shown

Sort Relevance Recently updated Fewest tokens Security grade Repo stars Stars this week Top rated 1 mods

simplemem-skill

aiming-lab/SimpleMem

Skill Claude CodeCodex

Store and retrieve conversation memories across sessions. Use when asked to 'remember this', 'save conversation', 'add to memory', 'what did we discuss about...', 'query memories', or 'import chat history'. Also use proactively to preserve important dialogue context and decisions.

not rated 3.8k +10 2mo ago A SkillSpector: pass 58 tokens original MIT