Pular para o conteúdo
TakoAPI
Voltar às skills

ralphie

por sirouk

Coding Agents & IDEs
—Ainda sem avaliações
Sua avaliação

Resumo

Install and operate Clawboard with OpenClaw.

Descrição

O que esta skill faz

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.

Quando usá-la

  • 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

Exemplo de fluxo de trabalho

ENTRADA

User asks: Install and configure Clawboard with my OpenClaw setup

AGENTE
  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

SAÍDA

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

Instalação

clawhub install sirouk/ralphie

Execute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.

Links