Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
SimpleMem
SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal
3.5kstars
360forks
Python
agentaudiocompressionknowledge-graphlifelong-memoryllmmcpmemorymultimodalpythonragretrieval
Quality signals
StaleNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
Store and retrieve long-term memories for AI agents with text, images, audio, or video using semantic compression.
Use this when
- building AI agents that remember past conversations
- storing multimodal context (images, audio, video) for agents
- reducing token costs by compressing long-term memory
- integrating memory into Claude, Cursor, or LM Studio
- needing cross-session memory for persistent AI workflows
Don't use when
- for short-term chatbots without memory needs
- when you only need keyword-based retrieval
- if you require exact text matching over semantic search
Capabilities
- stores text, images, audio, and video memories
- compresses memories with semantic lossless compression
- auto-selects text or multimodal backend on first method call
- self-evolving retrieval via LLM-driven closed-loop diagnosis
- supports MCP servers for text memory integration
- achieves SOTA on LoCoMo and Mem-Gallery benchmarks
Install
Universal installANY TOOL
$ npx skillcity@latest aiming-lab/SimpleMemAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Prefer to set it up by hand? Clone the repository:
git clone https://github.com/aiming-lab/SimpleMem.git
Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
simplemem — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt