A comprehensive guide to setting up Brave Search API and resolving network connectivity or proxy issues for Openclaw web tools.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install brave-search-setup
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install brave-search-setup using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
This skill provides a structured workflow for integrating the Brave Search API into your AI agent environment. It specifically addresses common networking hurdles encountered by developers, such as "fetch failed" errors and regional network restrictions. By utilizing these Openclaw Skills, users can ensure their agents have reliable, real-time access to web data.
The guide covers everything from initial API key injection to advanced system-level proxy configurations using tools like launchctl or proxychains-ng. This ensures that the underlying gateway process properly inherits the necessary network environment variables, making it an essential resource for maintaining robust web-connected agent workflows on macOS.
# Via config.patch to store the key securely
openclaw gateway config.patch --raw '{"tools":{"web":{"search":{"apiKey":"YOUR_BRAVE_API_KEY","enabled":true,"provider":"brave"}}}}'
# Set for current and future sessions
launchctl setenv HTTPS_PROXY http://127.0.0.1:7897
launchctl setenv HTTP_PROXY http://127.0.0.1:7897
# Enable restart command
openclaw gateway config.patch --raw '{"commands":{"restart":true}}'
# Perform restart
openclaw gateway restart
| Component | Configuration Key | Description |
|---|---|---|
| API Key | tools.web.search.apiKey |
Your unique Brave Search subscription token. |
| Provider | tools.web.search.provider |
Set to "brave" for this specific search integration. |
| Network | HTTPS_PROXY |
Environment variable used by the gateway for external requests. |
| Local Config | ~/.openclaw/openclaw.json |
The primary storage file for these Openclaw Skills settings. |
Loading
mnemo provides cloud-persistent, multi-agent memory for AI agents using TiDB Serverless to enable cross-session recall and hybrid vector search.

A network utility skill for retrieving public IP addresses and detailed geolocation information via CLI commands.

An automated media-sharing skill that selects and sends contextually relevant images and dance videos to messaging channels via OpenClaw.

An AI-powered speech-to-text skill that utilizes OpenAI Whisper to transcribe audio files into accurate text automatically.

A specialized workflow for extracting, translating, and summarizing verbatim transcripts from long YouTube videos using automated agent orchestration.

A specialized skill for aggregating and analyzing diverse perspectives from major global media outlets on significant news events.








































