菜单
Use MARM Memory to give Claude Code, Cursor, Codex, Gemini, and other MCP clients a local-first shared memory server with sessions, semantic recall, notebooks, summaries, and code graph context.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | Give MCP agents local shared memory with MARM |
| slug | give-mcp-agents-local-shared-memory-with-marm |
| description | Use MARM Memory to give Claude Code, Cursor, Codex, Gemini, and other MCP clients a local-first shared memory server with sessions, semantic recall, notebooks, summaries, and code graph context. |
| github_stars | 307 |
| verification | security_reviewed |
| source | https://github.com/Lyellr88/marm-memory |
| author | MARM Memory contributors |
| publisher_type | open_source |
| category | Integrations & Connectors |
| framework | MCP |
| tool_ecosystem | {"github_repo":"Lyellr88/marm-memory","github_stars":307} |
Use MARM Memory to give Claude Code, Cursor, Codex, Gemini, and other MCP clients a local-first shared memory server with sessions, semantic recall, notebooks, summaries, and code graph context.
MARM MCP server, Python or Docker runtime, SQLite-backed local storage, MCP-compatible clients such as Claude Code, Cursor, Codex, Gemini, Qwen, or VS Code agents
Use the upstream install or setup path that matches your environment:
Requirements and caveats from upstream:
Basic usage or getting-started notes:
"server_url": "https://your-marm-domain.example.com/mcp",
MARM handles lifecycle work internally. Docs and session state initialize on the first real tool call, and packaged docs are indexed into the marm_system memory namespace with source-file hash tracking, so your agent...
Extracted from upstream docs: https://raw.githubusercontent.com/Lyellr88/marm-memory/HEAD/README.md
Use Hunk to keep a live terminal review UI open for agent-authored code changes, with Git, Jujutsu, Sapling, patch input, watch mode, and inline agent annotations.
Use Cmux to run multiple AI coding-agent terminal sessions with visible notifications, scriptable panes, an in-app browser, and project-aware workspaces.
Use Sidekiq Scheduler to run recurring Ruby/Sidekiq agent jobs for refreshes, evaluations, reports, maintenance, and queue-driven automations with cron-style schedules.
Use MoAI-ADK to install Claude Code agents and skills for spec-first implementation, TDD, DDD, and quality-gated development.
Use Dkron to run recurring agent maintenance, data refresh, evaluation, and cleanup jobs across a fault-tolerant cluster with a UI and API.
Interactive browser skill for logged-in flows, dynamic pages, and session-aware site operations.
