CC

clawdata/clawdata

Developer tools

이 페이지는 AI로 자동 번역되었습니다. 기술적인 세부 사항은 원문을 확인하세요. 원문 보기

24 stars 품질 47 트렌드 10

Your own personal data engineer for OpenClaw.

개요

An easy-to-use dashboard, CLI, and FastAPI backend for managing OpenClaw agents built for data teams. Spin up agents that understand your pipelines, query your warehouses, generate dbt models, review SQL, and more — from the web UI or the terminal. Built for data engineers and analysts who want AI assistance without leaving their stack. Overview of your agents, system health, and quick actions. Talk to any agent directly. Switch agents, view connection status, and review conversation history. Set up agents with custom models, skills, and linked sub-agents. Browse, enable, and install skills for your agents — databases, APIs, data tools, and more. Track token usage and estimated costs across all agents and sessions. This starts: - at http://localhost:8000 (FastAPI + OpenClaw gateway) - at http://localhost:3000 (Next.js) Data is persisted in Docker volumes (clawdata-db, clawdata-userdata).

README

원문 README의 일부입니다. 원문 보기.

ClawData

An easy-to-use dashboard, CLI, and FastAPI backend for managing OpenClaw agents built for data teams. Spin up agents that understand your pipelines, query your warehouses, generate dbt models, review SQL, and more — from the web UI or the terminal. Built for data engineers and analysts who want AI assistance without leaving their stack.

Screenshots

Dashboard

Overview of your agents, system health, and quick actions.

Chat

Talk to any agent directly. Switch agents, view connection status, and review conversation history.

Agent Configuration

Set up agents with custom models, skills, and linked sub-agents.

Skills

Browse, enable, and install skills for your agents — databases, APIs, data tools, and more.

Costing

Track token usage and estimated costs across all agents and sessions.

Quick Start (Docker)

The fastest way to get running:

# Copy env and configure
cp .env.example .env
# Edit .env with your OpenClaw gateway token

# Start everything
docker compose up --build

This starts:

Data is persisted in Docker volumes (clawdata-db, clawdata-userdata).

To stop: docker compose down (add -v to also remove volumes/data).

Quick Start (Local)

# Create venv and install
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"

# Copy env and configure
cp .env.example .env
# Edit .env with your OpenClaw gateway token

# Run migrations
alembic upgrade head

# Start the server
uvicorn app.main:app --reload --port 8000

Frontend

cd web
npm install
npm run dev
# Open http://localhost:3000

CLI

ClawData includes an interactive CLI for managing agents and skills without the web UI:

# Launch the interactive menu
clawdata

# Or jump straight to a section
clawdata skills       # Toggle skills on/off per agent (↑↓ navigate, Space toggle, Enter confirm)
clawdata agents       # Browse, create, and configure agents
clawdata gateway      # Gateway health, logs, models, and providers
clawdata templates    # Browse project templates
clawdata status       # Quick system overview
clawdata setup        # Guided setup wizard
clawdata tui          # Launch the OpenClaw TUI

Skill management uses an interactive checklist — arrow keys to move, space bar to toggle, enter to apply:

  Skills for 🦞 main  (↑↓ navigate, Space toggle, Enter confirm)
> [x] Azure
  [ ] BigQuery
  [x] Data Analysis
  [x] Databricks Skill
  [ ] dbt
  [ ] DuckDB
  ...
GitHub에서 전체 README 보기

추천 도구

다른 키워드를 입력하거나 필터를 제거해 보세요.

설치

npx skillfish add clawdata/clawdata
MCP 초보자라면? mcpskill.org 가이드부터 시작하세요 →