MindMemOS

MindMemOS

A portable and self-evolving memory system for AI agents.

Agent SkillDevOpen source
Type
Agent Skill
Transport
http
Open source
Yes
GitHub Stars
★ 1.0k
Source
skill-github

Overview

MindMemOS is a memory operating system designed for AI agents, capable of accurately remembering user and task contexts and sharing them across different agents. It automatically refines skills through continuous interaction and connects to file-based knowledge systems, turning experience into real capability. Suitable for scenarios requiring cross-task accumulation and reuse of experience, domain knowledge, and constraints. Can be integrated via HTTP API, Python SDK/CLI, or agent plugins.

Capabilities

  • ▪Persistent user configuration across agents
  • ▪Self-evolving memory system
  • ▪Integration of memory and skills
  • ▪Multi-plugin support

Use cases

Long-term memory in algorithm design tasksCross-task experience accumulationReuse of domain knowledge and constraintsMemory sharing across multiple agents

Setup

Requires: API KeyNode 环境
Request an API Key from the official cloud service, or deploy locally: `cp .env.example .env` and `cp config/mindmemos/dev.example.yaml config/mindmemos/dev.yaml`, then refer to the deployment guide.

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How to get started with MindMemOS?

You can request an API Key from the official cloud service, or access it after local deployment.

What integration methods are supported?

Supports HTTP API, Python SDK/CLI, and agent plugins.

Related skills