agent-memory-mcp
面向 AI 代理的混合记忆系统,提供架构、模式和决策等知识的持久存储、搜索和管理。
译文已校对查看英文原文
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
适用对象:学习与科研。自动收录 · 待核查。
原作者说明节选
从固定版本的 SKILL.md 提取,保留原文语言。以下内容属于作者说明,本站尚未验证安装、兼容或运行结果。
查看英文原文
原文涵盖的主题
- Agent Memory Skill
- Prerequisites
- Setup
- Capabilities (MCP Tools)
- memorysearch
- memorywrite
- memoryread
- memorystats
This skill provides a persistent, searchable memory bank that automatically syncs with project documentation. It runs as an MCP server to allow reading/writing/searching of long-term memories. Node.js (v18+) 1. Clone the Repository: Clone the agentMemory project into your agent's workspace or a parallel directory: 2. Install Dependencies: 3. Start the MCP Server: Use the helper script to activate the memory bank for your current project: Example for current directory: Search for memories by query, type, or tags. Args: query (string), type? (string), tags? (string[]) Usage: "Find all authentication patterns" -> memorysearch({ query: "authentication", type: "pattern" }) Record new knowledge or decisions. Args: key (string), type (string), content (string), tags? (string[]) Usage: "Save this architecture decision" -> memorywrite({ key: "auth-v1", type: "decision", content: "..." }) Retrieve specific memory content by key. Args: key (string) Usage: "Get the auth design" -> memoryread({ key: "auth-v1" }) View analytics on memory usage. Usage: "Show memory statistics" -> memorystats({}) This skill includes a standalone dashboard to visualize memory usage. Access at: http://localhost:3333
- 来源仓库
- davila7/claude-code-templates
- 源文件
- cli-tool/components/skills/ai-research/agent-memory-mcp/SKILL.md
- 固定版本
- 21be197f100a12b8d0dd9a211cc244c8179f84d3
来源与内容状态
本条为自动发现的元数据,尚未完成人工文档核查;适用性与运行结果待核查。
原作者:davila7/claude-code-templates · 原作者仓库元数据。文档核查:未核查。最近来源检查:2026-11-09T14:01:42.945Z。
分类由名称、说明与路径规则生成,分类不代表已核实适配。
许可与权利归属
MIT。第三方内容及版权归原作者,使用条件以原文为准。
许可原文 ↗本站没有因同步、复制或用户自报成功而将资源标为运行验证通过。
限制与注意事项
- 元数据收录不代表本站已经安装、适配、实测或进行安全审查。