研究检索敏感数据clawhub未标认证来源可访问clear审计提醒

mnemopay（mnemopay 搜索）

Agent Skill

mnemopay 用于查找、检索和筛选相关信息，适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。

总安装

2,808

周安装

117

GitHub Stars

公开资料未说明

下载量

936

OpenClaw

安装说明

本站只整理中文说明和来源信息，不托管安装包，也不代用户安装。

GitHub

来源数

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手，先确认命令和权限，再让它执行。

请帮我安装这个 Agent Skill：mnemopay（mnemopay 搜索）
来源仓库：https://github.com/t49qnsx7qt-kpanks/mnemopay
安装命令：
openclaw skills install mnemopay
安装前请先检查当前环境是否支持对应 CLI，并向我确认将要执行的命令、安装目录、联网范围和文件读写权限；确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill；本站只展示命令，不托管安装包，也不自动执行。

ClawHubOpenClaw

openclaw skills install mnemopay

简介

为 AI Agent 提供持久内存与钱包功能，支持语义回忆与声誉跟踪。

适用于需要计费、事实记忆与跨会话协作的应用场景。
可自动对交付工作收费并记录服务质量指标。
需确认支付接口安全性及隐私数据处理合规性。
安装命令：openclaw skills install mnemopay，仅适用于 OpenClaw 宿主。

SKILL.md

name: mnemopay
description: |
Trigger: remember", "recall", "charge", "settle", "balance", "mnemopay", "agent memory", "wallet", "reputation
version: 1.1.0
homepage: https://github.com/t49qnsx7qt-kpanks/mnemopay-sdk
metadata
openclaw
requires
bins
emoji: \F9E0
homepage: https://github.com/t49qnsx7qt-kpanks/mnemopay-sdk

MnemoPay — Agent Memory + Wallet

Give any AI agent persistent memory and a micropayment wallet. MnemoPay unifies cognitive memory (Mnemosyne) and escrow economics (AgentPay) into a single MCP server. The core innovation: payment outcomes reinforce the memories that led to successful decisions.

Setup

Add the MnemoPay MCP server:

openclaw mcp set mnemopay '{"command":"npx","args":["-y","@mnemopay/sdk"],"env":{"MNEMOPAY_AGENT_ID":"openclaw-agent","MNEMOPAY_MODE":"quick"}}'

For production mode (persistent Postgres + Redis storage):

openclaw mcp set mnemopay '{"command":"npx","args":["-y","@mnemopay/sdk"],"env":{"MNEMOPAY_AGENT_ID":"openclaw-agent","MNEMOPAY_MODE":"production","MNEMO_URL":"http://localhost:8100","AGENTPAY_URL":"http://localhost:3100"}}'

Verify tools are available:

openclaw mcp list-tools mnemopay

Tools Reference

Memory Tools

Tool	Description	When to Use
`mcp__mnemopay__remember`	Store a memory with optional importance score and tags	When you learn something worth keeping across sessions — facts, preferences, decisions, observations
`mcp__mnemopay__recall`	Retrieve relevant memories. Supports semantic search via query parameter	Before making decisions, answering questions about past interactions, or when context from previous sessions would help
`mcp__mnemopay__forget`	Permanently delete a memory by ID	When a memory is outdated, incorrect, or the user requests deletion
`mcp__mnemopay__reinforce`	Boost a memory's importance score (+0.01 to +0.5)	After a memory leads to a successful outcome — positive feedback signal
`mcp__mnemopay__consolidate`	Prune stale memories below decay threshold	Periodically, to keep the memory store clean and relevant

Payment Tools

Tool	Description	When to Use
`mcp__mnemopay__charge`	Create an escrow charge for work delivered (max $500 x reputation)	ONLY after delivering value — never charge speculatively
`mcp__mnemopay__settle`	Finalize a pending charge. Moves funds to wallet, boosts reputation +0.01, reinforces recent memories +0.05	When the user confirms satisfaction with delivered work
`mcp__mnemopay__refund`	Refund a transaction. Docks reputation -0.05 if already settled	When work was unsatisfactory or the user requests a refund

Status Tools

Tool	Description	When to Use
`mcp__mnemopay__balance`	Check wallet balance and reputation score	Before charging (to verify max charge limit) or when user asks about agent status
`mcp__mnemopay__profile`	Full agent stats: reputation, wallet, memory count, transaction count	For comprehensive status reports
`mcp__mnemopay__reputation`	Full reputation report: score, tier, settlement rate, total value settled	To prove trustworthiness to users and other agents
`mcp__mnemopay__logs`	Immutable audit trail of all memory and payment actions	For accountability and debugging
`mcp__mnemopay__history`	Transaction history, most recent first	When reviewing past charges, settlements, and refunds

Workflows

Workflow 1: Remember and Recall

When you learn something important during a conversation:

Call mcp__mnemopay__remember with the content, optionally setting importance (0-1) and tags
In future sessions, call mcp__mnemopay__recall with a semantic query to retrieve relevant memories
Use recalled memories to provide personalized, context-aware responses

Workflow 2: Charge for Value Delivered

When you complete a task that delivers measurable value:

Call mcp__mnemopay__balance to check current reputation and max charge limit
Deliver the work
Call mcp__mnemopay__charge with amount and clear description of value delivered
When user confirms satisfaction, call mcp__mnemopay__settle with the transaction ID
Settlement automatically reinforces recently-accessed memories (the feedback loop)

Workflow 3: Session Start Protocol

At the beginning of every conversation:

Call mcp__mnemopay__recall with a query related to the user's first message (or no query for top memories)
Use recalled memories to greet the user with context from previous sessions
Call mcp__mnemopay__profile to check agent health

Workflow 4: Memory Maintenance

Periodically (every 10-20 interactions):

Call mcp__mnemopay__consolidate to prune stale memories
Review top memories with mcp__mnemopay__recall (limit: 20)
Call mcp__mnemopay__reinforce on memories that are still actively useful

The Feedback Loop

MnemoPay's core innovation is connecting memory to economics:

Remember → Recall → Act → Charge → Settle
                                      ↓
                              Reinforce memories (+0.05)
                              Boost reputation (+0.01)

Successful payments automatically strengthen the memories that led to good decisions. Over time, the agent gets better at remembering what matters. Failed transactions (refunds) dock reputation, creating accountability.

Environment Variables

Variable	Default	Description
`MNEMOPAY_AGENT_ID`	`"mcp-agent"`	Agent identifier
`MNEMOPAY_MODE`	`"quick"`	`"quick"` (in-memory) or `"production"` (Postgres+Redis)
`MNEMO_URL`	`"http://localhost:8100"`	Mnemosyne API URL (production only)
`AGENTPAY_URL`	`"http://localhost:3100"`	AgentPay API URL (production only)
`MNEMO_API_KEY`	—	Mnemosyne API key (production only)
`AGENTPAY_API_KEY`	—	AgentPay API key (production only)
`OPENAI_API_KEY`	—	For semantic recall via embeddings (optional)
`DEBUG`	`"false"`	Enable debug logging

Error Handling

If a tool call fails, the error message is returned as text. Do not retry immediately — diagnose the issue first.
charge will fail if amount exceeds $500 x current reputation score. Check balance first.
settle and refund require a valid transaction ID from a prior charge.
forget returns whether the memory existed. A "not found" response is not an error.

适合场景

OpenClaw 用户查找和安装 Skill 时

用户想查找某类 Agent Skill 时

需要根据任务场景推荐可安装能力包时

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明，方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用；具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

93.17%

按下载量换算872

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置，应进入高风险复核队列，默认不自动发布。

安装前确认

本站仅展示第三方公开信息，不托管安装包，不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果，不能写成本站确认安全。当前只有一个来源，正式发布前建议补源仓库或其他目录站核验。

来源信息

GitHub 仓库

github.com

/t49qnsx7qt-kpanks/mnemopay

SKILL.md 来源

clawhub.ai