Skip to main content
Glama
meharajM
by meharajM

Agentic Loop Memory Server ♾️

Agent Skills skills.sh

面向长期运行的智能体工作流的行业标准持久化记忆与状态管理器。

让任何 AI 模型——尤其是上下文窗口有限的小型模型——都能具备高端模型那样的持久性。本项目以两部分生态系统的形式运作:用于状态管理的 MCP Server 和用于编排的 Agent Skill

🛠 完整设置(必需)

为获得最佳体验,您必须同时安装编排技能和 MCP 服务器。

1. 安装技能

agentic-loop 技能安装到您的 AI 智能体(Codex、Claude Code、Cursor、Gemini CLI、GitHub Copilot 以及其他 Agent Skills 宿主):

npx skills add meharajM/agent-loop-mcp@agentic-loop -g -y

在激活前预览该技能:

gh skill preview meharajM/agent-loop-mcp agentic-loop

2. 配置 MCP 服务器

将以下内容添加到您的 mcp_config.json

{
  "mcpServers": {
    "agent-loop": {
      "command": "npx",
      "args": ["-y", "@mhrj/mcp-agent-loop"]
    }
  }
}

Related MCP server: hmem

🌟 为什么这种方法独一无二

与被动式记忆工具不同,这是一个主动状态管理器。它会监控字数以触发压缩周期,并在每次失败时强制执行"自愈策略",防止 AI 智能体陷入无意义的循环。

📂 项目结构

  • src/:MCP 服务器的 TypeScript 源码。

  • skills/agentic-loop/SKILL.md:面向 AI 的指令手册。

  • build/:JavaScript 构建产物。

📄 许可证

ISC

Install Server
A
license - permissive license
A
quality
B
maintenance

Maintenance

Maintainers
Response time
Release cycle
1Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

View all related MCP servers

Related MCP Connectors

  • Persistent memory for AI agents. Search, store, and recall across sessions.

  • Universal memory for AI agents and tools. Save, organize and search context anywhere.

  • Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/meharajM/agent-loop-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server