mnemopay

mnemopay is a skill for Claude Code from mnemopay/mnemopay-sdk. It costs 195 tokens per session (1,922 once invoked), scanned A, original, Apache-2.0.

A service that gives AI agents persistent memory and a wallet for small payments, working across several AI hosting environments. Persistent memory means information remains available between sessions.

In plain words
What is it for?
Setting up agent memory, recalling or storing information, managing micropayments and escrow, and connecting these functions through an MCP server.
Why use it?
It lets agents remember facts and automatically capture selected work such as commits, publications, and file writes without requiring every memory to be saved manually.

Skill for Claude Code

Written for Claude Code: UserPromptSubmit hook event. Also seen: mentions Claude Code; built for openclaw.

Good fit Setting up agent memory, recalling or storing information, managing micropayments and escrow, and connecting these functions through an MCP server.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mnemopay/mnemopay-sdk/openclaw
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add mnemopay/mnemopay-sdk --skill openclaw
Clone the repo
git clone --depth 1 https://github.com/mnemopay/mnemopay-sdk

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mnemopay

README.md
[![agentmods](https://agentmods.dev/badge/skills/mnemopay/mnemopay-sdk/openclaw/github.svg)](https://agentmods.dev/skills/mnemopay/mnemopay-sdk/openclaw)
Your own site
<a href="https://agentmods.dev/skills/mnemopay/mnemopay-sdk/openclaw"><img src="https://agentmods.dev/badge/skills/mnemopay/mnemopay-sdk/openclaw/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mnemopay

Your own site · 80×15
<a href="https://agentmods.dev/skills/mnemopay/mnemopay-sdk/openclaw"><img src="https://agentmods.dev/badge/skills/mnemopay/mnemopay-sdk/openclaw.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 195 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,922 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00195 $0.01922
Opus 5 $0.00097 $0.00961
Sonnet 5 $0.00039 $0.00384
Haiku 4.5 $0.00019 $0.00192

Measured 8d ago against content hash 46c72bdfe60e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mnemopay scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

integrations/openclaw/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

Auto-configure Claude Code hooks (session lifecycle, recall injection, auto-capture):

npx @mnemopay/sdk 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

Read the full file on GitHub · 156 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 156 lines · 195 tokens per session scan A 46c72bdfe60e

Subscribe to this mod's changes

mnemopay is a skill published in the GitHub repository mnemopay/mnemopay-sdk (8 stars, last pushed 20d ago), licensed Apache-2.0. It adds 195 tokens to every session and 1,922 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.