mnema

felipesauer/mnema
★ 1 stars TypeScript Database Updated 5d ago
A tamper-evident, local-first audit trail for AI-agent work — an MCP server with typed tools behind workflow gates and a signed, hash-chained log anyone can verify without a secret.
View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "mnema": {
      "command": "npx",
      "args": [
        "-y",
        "felipesauer/mnema"
      ]
    }
  }
}

README Excerpt

<h1 align="center"> <br> <img src="./docs/assets/logo.png" alt="mnema logo" width="180"> <br> mnema <br> </h1> <p align="center"><em>a tamper-evident audit chain for AI-agent work</em></p> <p align="center"> <a href="https://www.npmjs.com/package/@felipesauer/mnema"><img src="https://img.shields.io/npm/v/@felipesauer/mnema/alpha?style=flat-square&logo=npm&logoColor=white&label=npm%20alpha&color=cb3837" alt="npm alpha version"></a>

Tools (3)

advisoryblockingmcpServers

Topics

agent-governanceai-agentsaudit-trailclaude-codecryptographic-verificationcursored25519local-firstmcpmodel-context-protocolprovenancesqlitetamper-evident
📊
Working with market or time-series data?
The Polymarket Historical Dataset — 18.5M+ price snapshots across 18,600+ prediction markets (CSV + SQLite). Built for backtesting & ML.
View dataset →