Skip to main content
ClaudeWave
EN, English
aiming-lab / Subagents

SimpleMem

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

  • 3.8k stars
  • 408 forks
  • 18 open issues
  • Language: Python
  • License: MIT
  • updated
Install in ClaudeView on GitHub

Install

Terminal
git clone https://github.com/aiming-lab/SimpleMem && cp SimpleMem/*.md ~/.claude/agents/
  1. Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).
  2. Start a new Claude Code session to load the agents.
  3. Delegate work to them with the Task/Agent tool or by name.

Editor's note

SimpleMem is a Python library and MCP server that gives LLM agents persistent, long-term memory across text, image, audio, and video modalities. Its three core components are SimpleMem (text memory with semantic lossless compression), Omni-SimpleMem (multimodal memory handling images, audio, and video alongside text), and EvolveMem, a self-evolving retrieval layer that uses an LLM-driven closed-loop diagnosis loop to discover new retrieval dimensions autonomously. All three are unified under a single `pip install simplemem` package with automatic backend routing via `from simplemem import SimpleMem`. The MCP server at mcp.simplemem.cloud connects directly to Claude Desktop and any other MCP-compatible client for text memory, while full multimodal support is available through direct Python integration. On the LoCoMo benchmark, Omni-SimpleMem achieves an F1 of 0.613, a 47 percent improvement over the previous best, and EvolveMem adds a further relative gain of 25.7 percent. Developers building agents, RAG pipelines, or long-horizon assistants that need cross-session recall across multiple media types are the primary audience.

Installable items

1 items in this repository

simplemem-skillSkill

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.

Install
README

Subagents overview

README preview not available. Visit the repo on GitHub for full documentation.
Use cases
AI / ML Creative Dev Tools
Topics
agentaudiocompressionknowledge-graphlifelong-memoryllmmcpmemorymultimodalpythonragretrievalsemantic-searchsimplememvideovision
Frequently asked

What people ask about SimpleMem

What is aiming-lab/SimpleMem?

aiming-lab/SimpleMem is subagents for the Claude AI ecosystem. [ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal It has 3.8k GitHub stars and its last recorded update is dated 2026-07-24.

How do I install SimpleMem?

You can install SimpleMem by cloning the repository (https://github.com/aiming-lab/SimpleMem) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.

Is aiming-lab/SimpleMem safe to use?

Our security agent has analyzed aiming-lab/SimpleMem and assigned a Trust Score of 87/100 (tier: Trusted). See the full breakdown of passed checks and flags on this page.

Who maintains aiming-lab/SimpleMem?

aiming-lab/SimpleMem is maintained by aiming-lab. The last recorded GitHub activity is dated 2026-07-24, with 18 open issues.

Are there alternatives to SimpleMem?

Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.