Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- No code or documentation changes detected in this version. - This release maintains all previous functionality and instructions.
What This Skill Does
FreeRide configures OpenClaw to use free AI models from OpenRouter. It ranks available free models by quality, sets the best as primary, and builds a fallback chain so rate limits don't interrupt agent workflows. Updates only the model keys in openclaw.json without touching other config.
Automates free-model discovery and ranking on OpenRouter so users don't have to manually find, compare, and configure models in openclaw.json.
When to use it
- Cutting AI costs by switching to free OpenRouter models
- Setting up automatic model rotation when rate limits hit
- Adding fallback models without changing the current primary
- Trying different free LLMs without editing config files manually
- Keeping agents running uninterrupted during high-traffic periods
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Set up free AI models for my OpenClaw agents
- 1Verify OPENROUTER_API_KEY is set in the environment
- 2Run `freeride auto` to fetch and rank all available free models
- 3Write the top-ranked model to agents.defaults.model.primary in openclaw.json
- 4Add ranked fallbacks with openrouter/free as the first entry
- 5Run `openclaw gateway restart` to apply the new configuration
OpenClaw is now using the best available free model as primary with multiple ranked fallbacks. The user can verify the active model by sending /status.
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.