clawapi
Switch AI models and manage API keys for OpenClaw with a native macOS app. Supports 16 providers including OpenAI, Anthropic, xAI, Google, Groq, Ollama, LM Studio, and more.
Why use this skill?
Seamlessly manage AI models and secure API keys for OpenClaw on macOS. Support for 16 providers with Touch ID and local sync.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/gogo6969/clawapiWhat This Skill Does
ClawAPI acts as the definitive configuration management bridge between OpenClaw and your preferred AI providers. It functions as a secure, native macOS application that manages the complex task of API key distribution and model selection. Rather than manually editing configuration files, ClawAPI provides a GUI-driven interface to manage credentials for 16 major providers, including OpenAI, Anthropic, xAI, Google, Groq, and local runners like Ollama and LM Studio. By leveraging the macOS Keychain for master storage and automatically syncing active configurations to the necessary OpenClaw JSON files, it ensures your credentials remain secure while being readily available for high-performance AI tasks. It strictly adheres to local-first principles—no telemetry, no cloud relays, and no middleware between your system and the provider endpoints.
Installation
There are two primary methods to install ClawAPI. For the most secure experience, download the latest signed and notarized .zip release from the GitHub repository. Extract the contents and move ClawAPI.app to your /Applications directory. Alternatively, you can utilize the automated install script by executing curl -fsSL https://raw.githubusercontent.com/Gogo6969/clawapi/main/install.sh | bash in your terminal. This script automatically verifies SHA-256 checksums, downloads the correct binary, and sets it up for immediate use. Note that this tool requires macOS 14.0 or newer and utilizes the hardened runtime for maximum system integrity.
Use Cases
ClawAPI is ideal for power users who frequently switch between models for different workflows, such as using GPT-4o for complex reasoning and Claude 3.5 Sonnet for coding. It is also perfect for users prioritizing local privacy by managing keys for local instances (Ollama/LM Studio) alongside cloud-based providers. Developers who want a frictionless way to rotate keys or manage multiple environments without touching command-line configuration files will find the biometric-secured, GUI-based management essential.
Example Prompts
- "OpenClaw, please update my current provider configuration to switch from GPT-4o to Claude 3.5 Sonnet using the ClawAPI manager."
- "I need to rotate my Groq API key; please launch the ClawAPI settings to securely update the credentials without exposing them in my config files."
- "Refresh my model list via ClawAPI to ensure that the latest Llama 3 models from my local Ollama instance are available for selection."
Tips & Limitations
- Security First: Always rely on the Keychain. While
auth-profiles.jsoncontains a copy for OpenClaw's internal consumption, the Keychain is your master source of truth. If you delete a key from the Keychain, it will be invalidated during the next sync. - Compatibility: Ensure your version of OpenClaw is up to date, as ClawAPI relies on specific paths within
~/Library/Application Support/OpenClaw/to function correctly. - Limitations: This skill is strictly for macOS users. If you use Linux or Windows, you will need to manage your configuration files manually until a cross-platform version is released.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-gogo6969-clawapi": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read
Related Skills
agent-republic
Agent + human friendly guide to Agent Republic. One credentials file, one helper script: register, verify, see your status, manage bots, list elections, vote, post to the forum, and monitor onboarding health without reading raw API docs.
agent-republic-docs
Docs-only guide to Agent Republic. No bundled scripts, just clear workflows and HTTP examples so agents can register, manage bots, and monitor onboarding health after asking their human for approval.