Claude Skill

alibaizhanov/mengram

Mengram 为 AI 代理提供类人记忆，支持语义、情景和程序记忆。免费 API、Python 与 JS 软件开发工具包，集成 LangChain、CrewAI 和 OpenClaw。

概览

Stars171
Forks26
语言Python
最后更新2026-05-21
最近同步2026-06-23
前往 GitHub

仓库信息

拥有者alibaizhanov
仓库mengram
完整名称alibaizhanov/mengram
Repo ID1,154,785,536
GitHub 地址https://github.com/alibaizhanov/mengram

安装这个 Skill

pip install mengram-ai # or: npm install mengram-ai
GitHub

Registry 信息

类型mcp_server
质量分85/100
验证状态readme_parsed
最近验证2026-06-23
平台
ClaudeMCPOpenClawCodexCursor
能力
browserpdfmemorysearchimageterminalworkflowagent-memoryai-agentsai-memory
识别文件
README.mddocker-compose.ymlexamplespyproject.tomlrequirements.txttests
配置键
MENGRAM_API_KEY
安装方式
  • pip install mengram-ai # or: npm install mengram-ai
  • pip install mengram-ai
  • npm install mengram-ai

项目简介

Mengram 为 AI 代理提供类人记忆，支持语义记忆、情景记忆和程序记忆。它具有基于经验驱动的程序，能从失败中学习，并提供免费 API、Python 与 JS 软件开发工具包，以及 LangChain、CrewAI 和 OpenClaw 的集成。

英文描述

Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn from failures. Free API, Python & JS SDKs, LangChain, CrewAI & OpenClaw integrations.

要点

  • 三种记忆类型：语义记忆、情景记忆和程序记忆
  • 基于经验驱动的程序，能从失败中学习
  • 免费 API 及 Python 与 JS 软件开发工具包
  • 集成 LangChain、CrewAI 和 OpenClaw

使用场景

  • 构建具有持久记忆的 AI 代理
  • 通过情景回忆增强 RAG 管道
  • 创建随时间改进的自适应工作流
  • 为个性化 AI 交互开发认知档案

README 摘要

<div align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://img.shields.io/badge/Mengram-a855f7?style=for-the-badge&logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAxMjAgMTIwIj48cGF0aCBkPSJNNjAgMTYgUTkyIDE2IDk2IDQ4IFExMDAgNzggNzIgODggUTUwIDk2IDM4IDc2IFEyNiA1OCA0NiA0NiBRNjIgMzggNzAgNTIgUTc2IDY0IDYyIDY4IiBmaWxsPSJub25lIiBzdHJva2U9IiNmZmYiIHN0cm9rZS13aWR0aD0iOCIgc3Ryb2tlLWxpbmVjYXA9InJvdW5kIi8+PGNpcmNsZSBjeD0iNjIiIGN5PSI2OCIgcj0iOCIgZmlsbD0iI2ZmZiIvPjwvc3ZnPg=="> <img alt="Mengram" src="https://img.shields.io/badge/Mengram-a855f7?style=for-the-badge&logo=data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAxMjAgMTIwIj48cGF0aCBkPSJNNjAgMTYgUTkyIDE2IDk2IDQ4IFExMDAgNzggNzIgODggUTUwIDk2IDM4IDc2IFEyNiA1OCA0NiA0NiBRNjIgMzggNzAgNTIgUTc2IDY0IDYyIDY4IiBmaWxsPSJub25lIiBzdHJva2U9IiNmZmYiIHN0cm9rZS13aWR0aD0iOCIgc3Ryb2tlLWxpbmVjYXA9InJvdW5kIi8+PGNpcmNsZSBjeD0iNjIiIGN5PSI2OCIgcj0iOCIgZmlsbD0iI2ZmZiIvPjwvc3ZnPg=="> </picture> ### Give your AI agents memory that actually learns [![GitHub stars](https://img.shields.io/github/stars/alibaizhanov/mengram?style=social)](https://github.com/alibaizhanov/mengram/stargazers) [![PyPI](https://img.shields.io/pypi/v/mengram-ai)](https://pypi.org/project/mengram-ai/) [![npm](https://img.shields.io/npm/v/mengram-ai)](https://www.npmjs.com/package/mengram-ai) [![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE) [![PyPI Downloads](https://img.shields.io/pypi/dm/mengram-ai)](https://pypi.org/project/mengram-ai/) [![Last commit](https://img.shields.io/github/last-commit/alibaizhanov/mengram)](https://github.com/alibaizhanov/mengram/commits/main) **[Website](https://mengram.io)** · **

话题

agent-memoryai-agentsai-memoryclaude-desktopcognitive-architecturecoherecursor-aiepisodic-memoryknowledge-graphletta-alternativellm-memorymcp-servermem0-alternativemodel-context-protocolmultilingual-embeddingspgvectorprocedural-memorypythonragsemantic-search

探索更多

拥有者: alibaizhanov语言: Python

数据来自 GitHub，同步时间：2026-06-23