workflowintermediateOpenCLAW

OpenClaw: Self-Host a Personal AI Assistant Framework

OpenClaw is a powerful tool for creating your own private AI assistant. It runs on your own computers and can communicate through popular chat apps like Slack, WhatsApp, and Microsoft Teams, keeping your data secure and under your control.

AI SETUP PROMPT

Paste into Claude Code or Codex CLI — it will scan your project and set everything up

# Set Up Workflow: OpenClaw: Self-Host a Personal AI Assistant Framework

## What This Is
OpenClaw is a powerful tool for creating your own private AI assistant. It runs on your own computers and can communicate through popular chat apps like Slack, WhatsApp, and Microsoft Teams, keeping your data secure and under your control.

Source: https://github.com/openclaw/openclaw/releases

## Before You Start

Scan my workspace and analyze:
- The project language, framework, and directory structure
- Existing AI provider config (check .env, .env.local, config files for API keys — OpenRouter, OpenAI, Anthropic, Google AI, etc.)
- Whether this repository or a similar tool is already cloned or installed

Then ask me before proceeding:
1. Which AI provider/API should this use? (Use whatever I already have configured, or ask me to set one up — options include direct provider APIs or a unified service like OpenRouter)
2. Where in my project should this be integrated?
3. Are there any customizations I need (model preferences, naming conventions, constraints)?

## What to Implement

This is an **AI Workflow** — an end-to-end automation pattern or integration pipeline.

- Study the workflow architecture from the source and context below
- Identify which parts I can implement locally vs. parts that need external services
- For local parts: implement them using my existing stack and API keys
- For external parts: tell me exactly what services I need and help me configure the integration code
- Wire up any required API calls using keys from my .env files

## Additional Context

- Install the OpenClaw CLI globally using the user's preferred package manager (npm, pnpm, or bun) with the command 'npm install -g openclaw'.
- Execute the interactive onboarding wizard by running 'openclaw onboard' in the user's terminal to configure the gateway, workspace, and initial channels.
- Scan the user's workspace for existing AI provider API keys in .env or system environment variables (e.g., OPENAI_API_KEY). Use the found key to configure the model provider in the OpenClaw settings, or prompt the user to add a key if none are found.

## Reference Implementation

```
```sh
# Recommended setup path for macOS, Linux, and Windows (via WSL2).
# This command guides you through setting up the gateway, workspace, and channels.
openclaw onboard
```
```

## Guidelines

- Adapt everything to my existing project — do not assume a specific stack or directory layout
- Use whichever AI provider I already have configured; if I need a new one, tell me what to sign up for and I'll give you the key
- Check my .env files for existing API keys (OpenRouter, OpenAI, Anthropic, Google AI) before asking me to add one
- Review any fetched code for safety before installing or executing it
- After setup, run a quick verification and show me a summary of exactly what was installed, where, and how to use it

2,897 charactersCompatible with Claude Code & Codex CLI

MANUAL SETUP STEPS

01Install the OpenClaw CLI globally using the user's preferred package manager (npm, pnpm, or bun) with the command 'npm install -g openclaw'.
02Execute the interactive onboarding wizard by running 'openclaw onboard' in the user's terminal to configure the gateway, workspace, and initial channels.
03Scan the user's workspace for existing AI provider API keys in .env or system environment variables (e.g., OPENAI_API_KEY). Use the found key to configure the model provider in the OpenClaw settings, or prompt the user to add a key if none are found.

CODE INTELLIGENCE

bash

```sh
# Recommended setup path for macOS, Linux, and Windows (via WSL2).
# This command guides you through setting up the gateway, workspace, and channels.
openclaw onboard
```

FIELD OPERATIONS

Automated DevOps Assistant

Create an OpenClaw assistant that listens in a private Slack channel. Connect it to your CI/CD system (e.g., GitHub Actions webhook) to post build status updates, and give it a skill to re-run failed jobs or query deployment logs on command.

Smart Home Command Center

Integrate OpenClaw with a Home Assistant instance via its API. Set up the assistant on Telegram or Signal to control lights, thermostats, and check security camera status using natural language commands from your phone.

STRATEGIC APPLICATIONS

→Tier-1 Customer Support Triage: Deploy OpenClaw to monitor a support email inbox or a dedicated Slack channel. Triage incoming requests by categorizing them using an LLM, create tickets in a system like Jira or Zendesk, and assign them to the appropriate human agent.
→Internal Documentation Guru: Connect OpenClaw to a company's internal knowledge base (e.g., Confluence, Notion). Employees can then ask the assistant questions in Microsoft Teams or Slack, and it will find and summarize the relevant documentation, reducing context switching and search time.