Mnemos Memory
Mnemos is a local-first memory layer for coding agents. Use this skill to guide users or OpenClaw agents onto the supported install path, explain the operating loop, and keep compatibility claims accurate.
Default path
- - Prefer
pip install "mnemos-memory[mcp]" and mnemos ui. - For OpenClaw / ClawHub, teach the agent to self-install
mnemos-memory[mcp], run mnemos ui, then wire mnemos-mcp to the canonical MNEMOS_CONFIG_PATH before relying on memory. - Recommend SQLite as the supported persistent store.
- Recommend a real embedding provider (
openclaw, openai, openrouter, or ollama) for production retrieval quality. - Validate setup with the control-plane smoke check or
mnemos-cli doctor.
Claim discipline
- - Safe to claim: local-first scoped memory, MCP tools, SQLite starter profile, Claude Code plugin flow, documented Codex flow.
- Be explicit that deterministic auto-memory is shipped for Claude Code via hooks.
- For Codex, Cursor, OpenClaw, and generic MCP hosts, do not imply automatic capture unless the host has its own automation or the user adds one.
- Do not present removed legacy backends as available runtime options.
Workflow
- 1. Identify the host: Claude Code, Cursor, Codex, OpenClaw, or generic MCP.
- If the repo is available locally, read
README.md, docs/MCP_INTEGRATION.md, and docs/codex.md before answering. - Give the default install path first. Only fall back to manual config snippets if the user cannot use the control plane.
- Explain the operating loop:
-
mnemos_retrieve at task start
-
mnemos_store for durable facts only
-
mnemos_consolidate before finishing substantial work
-
mnemos_inspect when a stored fact looks wrong
- 5. Read
references/hosts.md for host-specific config snippets and caveats, especially the OpenClaw / ClawHub self-install flow when the agent must bootstrap itself. - Read
references/operations.md for automation, capture-mode, storage guidance, and troubleshooting.
Avoid
- - Do not tell users to manually type memories as the primary workflow.
- Do not recommend
SimpleEmbeddingProvider for production retrieval quality. - Do not suggest external storage backends for Mnemos. Keep users on the SQLite path.
Mnemos 记忆
Mnemos 是一个面向编码智能体的本地优先记忆层。使用此技能可引导用户或 OpenClaw 智能体进入支持的安装路径，解释操作循环，并保持兼容性声明的准确性。
默认路径
- - 优先使用 pip install mnemos-memory[mcp] 和 mnemos ui。
- 对于 OpenClaw / ClawHub，教导智能体自行安装 mnemos-memory[mcp]，运行 mnemos ui，然后在依赖记忆之前将 mnemos-mcp 连接到规范的 MNEMOSCONFIGPATH。
- 推荐 SQLite 作为支持的持久化存储。
- 推荐使用真实的嵌入提供方（openclaw、openai、openrouter 或 ollama）以获得生产级检索质量。
- 通过控制平面冒烟检查或 mnemos-cli doctor 验证设置。
声明规范
- - 可安全声明的内容：本地优先的作用域记忆、MCP 工具、SQLite 入门配置、Claude Code 插件流程、有文档记录的 Codex 流程。
- 明确说明通过钩子为 Claude Code 提供了确定性自动记忆功能。
- 对于 Codex、Cursor、OpenClaw 和通用 MCP 主机，除非该主机拥有自己的自动化机制或用户添加了自动化，否则不要暗示自动捕获。
- 不要将已移除的遗留后端呈现为可用的运行时选项。
工作流程
- 1. 识别主机：Claude Code、Cursor、Codex、OpenClaw 或通用 MCP。
- 如果仓库在本地可用，在回答前先阅读 README.md、docs/MCP_INTEGRATION.md 和 docs/codex.md。
- 首先给出默认安装路径。仅在用户无法使用控制平面时，才回退到手动配置片段。
- 解释操作循环：
- 任务开始时执行 mnemos_retrieve
- 仅对持久化事实执行 mnemos_store
- 完成重要工作前执行 mnemos_consolidate
- 当存储的事实看起来有误时执行 mnemos_inspect
- 5. 阅读 references/hosts.md 了解特定主机的配置片段和注意事项，特别是当智能体必须自行引导时的 OpenClaw / ClawHub 自安装流程。
- 阅读 references/operations.md 了解自动化、捕获模式、存储指南和故障排除。
避免事项
- - 不要告诉用户将手动输入记忆作为主要工作流程。
- 不要推荐使用 SimpleEmbeddingProvider 进行生产级检索。
- 不要为 Mnemos 建议外部存储后端。让用户保持在 SQLite 路径上。
