agent-memory-mcp
starsforks
How to install agent-memory-mcp?
samarthakv29/antigravity-god-mode/agent-memory-mcp
$npx -y skills add SamarthaKV29/antigravity-god-mode --skill agent-memory-mcpA hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
SKILL.md
| 1 | # Agent Memory Skill |
| 2 | |
| 3 | 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. |
| 4 | |
| 5 | ## Prerequisites |
| 6 | |
| 7 | - Node.js (v18+) |
| 8 | |
| 9 | ## Setup |
| 10 | |
| 11 | 1. **Clone the Repository**: |
| 12 | Clone the `agentMemory` project into your agent's workspace or a parallel directory: |
| 13 | |
| 14 | ```bash |
| 15 | git clone https://github.com/webzler/agentMemory.git .agent/skills/agent-memory |
| 16 | ``` |
| 17 | |
| 18 | 2. **Install Dependencies**: |
| 19 | |
| 20 | ```bash |
| 21 | cd .agent/skills/agent-memory |
| 22 | npm install |
| 23 | npm run compile |
| 24 | ``` |
| 25 | |
| 26 | 3. **Start the MCP Server**: |
| 27 | Use the helper script to activate the memory bank for your current project: |
| 28 | |
| 29 | ```bash |
| 30 | npm run start-server <project_id> <absolute_path_to_target_workspace> |
| 31 | ``` |
| 32 | |
| 33 | _Example for current directory:_ |
| 34 | |
| 35 | ```bash |
| 36 | npm run start-server my-project $(pwd) |
| 37 | ``` |
| 38 | |
| 39 | ## Capabilities (MCP Tools) |
| 40 | |
| 41 | ### `memory_search` |
| 42 | |
| 43 | Search for memories by query, type, or tags. |
| 44 | |
| 45 | - **Args**: `query` (string), `type?` (string), `tags?` (string[]) |
| 46 | - **Usage**: "Find all authentication patterns" -> `memory_search({ query: "authentication", type: "pattern" })` |
| 47 | |
| 48 | ### `memory_write` |
| 49 | |
| 50 | Record new knowledge or decisions. |
| 51 | |
| 52 | - **Args**: `key` (string), `type` (string), `content` (string), `tags?` (string[]) |
| 53 | - **Usage**: "Save this architecture decision" -> `memory_write({ key: "auth-v1", type: "decision", content: "..." })` |
| 54 | |
| 55 | ### `memory_read` |
| 56 | |
| 57 | Retrieve specific memory content by key. |
| 58 | |
| 59 | - **Args**: `key` (string) |
| 60 | - **Usage**: "Get the auth design" -> `memory_read({ key: "auth-v1" })` |
| 61 | |
| 62 | ### `memory_stats` |
| 63 | |
| 64 | View analytics on memory usage. |
| 65 | |
| 66 | - **Usage**: "Show memory statistics" -> `memory_stats({})` |
| 67 | |
| 68 | ## Dashboard |
| 69 | |
| 70 | This skill includes a standalone dashboard to visualize memory usage. |
| 71 | |
| 72 | ```bash |
| 73 | npm run start-dashboard <absolute_path_to_target_workspace> |
| 74 | ``` |
| 75 | |
| 76 | Access at: `http://localhost:3333` |
People who liked this also viewed
6 picksType
- lark-drive飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sSkillsJul 2026
- lark-sharedUse for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handlingSkillsJul 2026
- lark-whiteboard飞书画板：查询和编辑飞书云文档中的画板。支持导出画板为预览图片、导出原始节点结构、使用多种格式更新画板内容。 当用户需要查看画板内容、导出画板图片、编辑画板时使用此 skill。不负责：飞书云文档内容编辑（lark-doc）、文档内嵌电子表格/Base（lark-sheets / lark-base）。SkillsJul 2026
- lark-task飞书任务：管理任务、清单和任务智能体。创建待办任务、查看和更新任务状态、拆分子任务、组织任务清单、分配协作成员、上传任务附件、注册或注销任务智能体、更新任务智能体的主页数据、写入智能体任务记录。当用户需要创建待办事项、查看任务列表、跟踪任务进度、管理项目清单或给他人分配任务、为任务上传附件文件、注册注销任务智能体、更新智能体主页数据、写入任务记录时使用。SkillsJul 2026
- lark-attendance飞书考勤打卡：查询自己的考勤打卡记录SkillsJul 2026
- lark-apps妙搭（Spark/Miaoda）应用开发与托管：应用创建、本地全栈开发、云端生成迭代、创意设计（UI mockup / 可交互原型 / 线框图 / 落地页 / 仪表盘 / 幻灯片 deck / 视觉探索）、AI相关能力和飞书平台能力或者其他外部能力集成、日志/Trace/监控指标/PV/UV 查询、环境变量管理、应用角色与成员管理、自动化触发器（定时/记录变更/Webhook/飞书审批）。当用户要SkillsJul 2026
