技能详情（站内镜像，无评论）
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v0.3.0
统计：⭐ 0 · 115 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：可疑 · OpenClaw ：良性
Package：anthony-maio/mnemos-memory
安全扫描（ClawHub）
- VirusTotal ：可疑
- OpenClaw ：良性
OpenClaw 评估
The skill is an instruction-only guide for installing and operating Mnemos memory for agents and its requirements and instructions are coherent with that purpose.
综合结论
This skill is a focused how-to for installing and operating Mnemos. Before following it: ensure you trust the Mnemos package source (pip from PyPI or your approved repository), run installs in a virtualenv or sandbox, and review MNEMOS_CONFIG_PATH contents after wiring it. Be aware that production-quality retrieval requires external embedding providers (you'll need to supply their API keys and handle costs). If you plan to let an agent self-bo…
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「Mnemos Memory」。简介：Use when users or OpenClaw/ClawHub agents need to install, configure, self-boot…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/anthony-maio/mnemos-memory/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: mnemos-memory
description: Use when users or OpenClaw/ClawHub agents need to install, configure, self-bootstrap, troubleshoot, or operate Mnemos for persistent scoped agent memory, or when they mention Mnemos, agent memory, scoped memory, memory MCP tools, or memory automation.
---
# 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 starter store unless the user already has a scale reason for Qdrant or Neo4j.
- 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.
- Neo4jStore is experimental. Do not present it as graph-native spreading-activation persistence yet.
## Workflow
1. Identify the host: Claude Code, Cursor, Codex, OpenClaw, or generic MCP.
2. If the repo is available locally, read `README.md`, `docs/MCP_INTEGRATION.md`, and `docs/codex.md` before answering.
3. Give the default install path first. Only fall back to manual config snippets if the user cannot use the control plane.
4. 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.
6. 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 upgrade users to Qdrant or Neo4j unless they actually need a non-SQLite profile.