跳到正文
TakoAPI
返回技能列表

ralphie

由 sirouk 提供

Coding Agents & IDEs
—暂无评分
你的评分

简介

Install and operate Clawboard with OpenClaw.

描述

该技能的功能

Clawboard is a self-hosted logging and retrieval system for OpenClaw AI gateway traffic. It runs as a Docker stack with a Next.js web UI, FastAPI backend, Qdrant vector index, and a background classifier, capturing conversations through the clawboard-logger plugin. Retrieval combines dense vectors, BM25, and lexical matching with reciprocal rank fusion.

Keeps all conversation logs on your own infrastructure with no third-party data sharing, while still offering vector search, reranking, and a web UI.

何时使用

  • Searching past OpenClaw conversations by topic or keyword
  • Monitoring AI gateway response times across sessions
  • Reviewing a full history of prompts and completions
  • Backing up curated OpenClaw memories to a private GitHub repo
  • Running a self-hosted conversation index without cloud exposure

示例工作流

输入

User asks: Install and configure Clawboard with my OpenClaw setup

智能体
  1. 1

    Run the bootstrap script to clone the repo and detect the OpenClaw workspace layout

  2. 2

    Generate CLAWBOARD_TOKEN and write environment variables to .env

  3. 3

    Start Docker services: web, api, classifier, and qdrant

  4. 4

    Install and enable the clawboard-logger plugin in OpenClaw

  5. 5

    Restart the OpenClaw gateway and validate API health and search endpoints

输出

Clawboard running at localhost:3010 with logging active; search returning results from OpenClaw conversations

安装

clawhub install sirouk/ralphie

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接