Skip to content

FreeRide

FreeRide gives you unlimited free AI in OpenClaw by automatically managing OpenRouter's free models.

Install

$npx clawhub@latest install free-ride
Claude Code
claude mcp add freeride -- npx clawhub@latest install free-ride
Cursor / Claude Desktop (mcp.json)
{
  "mcpServers": {
    "freeride": {
      "command": "npx",
      "args": [
        "clawhub@latest",
        "install",
        "free-ride"
      ]
    }
  }
}

Install command taken from the project's README or registry entry. Always review code before running it.

🎢 FreeRide

Stop paying for AI. Start riding free.


🚀 FreeRide v3 is out — works with any OpenAI-compatible agent

The version on this repo (v2) is OpenClaw-specific and OpenRouter-only. FreeRide v3 is a local OpenAI-compatible gateway that routes across 5 free-tier providers (OpenRouter, Groq, NVIDIA NIM, Cloudflare Workers AI, HuggingFace) with automatic failover, and works with Aider, Continue, Hermes, OpenClaw, the OpenAI Python SDK, and any other OpenAI-shaped client.

curl -sSL https://api.free-ride.xyz/install.sh | sh
export OPENROUTER_API_KEY=sk-or-v1-...
freeride serve

Then point any agent at http://localhost:11343/v1 — or use a binder:

freeride bind aider       # writes ~/.aider.conf.yml
freeride bind continue    # writes ~/.continue/config.yaml
freeride bind hermes      # writes ~/.hermes/config.yaml
freeride bind openclaw    # writes ~/.openclaw/openclaw.json

👉 Repo: https://github.com/Shaivpidadi/FreeRideV3 · Site: https://free-ride.xyz · PyPI: pip install freeride-gateway

The v2 surface below still works for existing OpenClaw users — v3 ships v2 backwards-compat shims (freeride auto/list/switch/...), so an in-place upgrade preserves your existing setup.


FreeRide gives you unlimited free AI in OpenClaw by automatically managing OpenRouter's free models.

You: *hits rate limit*
FreeRide: "I got you." *switches to next best model*
You: *keeps coding*

The Problem

You're using OpenClaw. You love it. But:

  • 💸 API costs add up fast
  • 🚫 Free models have rate limits
  • 😤 Manually switching models is annoying
  • 🤷 You don't know which free model is actually good

The Solution

One command. Free AI. Forever.

freeride auto

That's it. FreeRide:

  1. Finds the 30+ free models on OpenRouter
  2. Ranks them by quality (context length, capabilities, speed)
  3. Sets the best one as your primary
  4. Configures smart fallbacks for when you hit rate limits
  5. Preserves your existing OpenClaw config

Installation

npx clawhub@latest install free-ride
cd ~/.openclaw/workspace/skills/free-ride
pip install -e .

That's it. freeride and freeride-watcher are now available as global commands.

Quick Start

1. Get a Free OpenRouter Key

Go to openrouter.ai/keys → Create account → Generate key

No credit card. No trial. Actually free.

2. Set Your Key

export OPENROUTER_API_KEY="sk-or-v1-..."

# Or, multiple keys (shown in `freeride status`):
export OPENROUTER_API_KEY='["sk-or-v1-key1","sk-or-v1-key2"]'

Or add it to your OpenClaw config:

openclaw config set env.OPENROUTER_API_KEY "sk-or-v1-..."

3. Run FreeRide

freeride auto

4. Restart OpenClaw

openclaw gateway restart

5. Verify It Works

Message your agent on WhatsApp/Telegram/Discord or the dashboard:

You:    /status
Agent:  (shows the free model name + token count)

Done. You're now running on free AI with automatic fallbacks.

What You Get

Primary Model: openrouter/nvidia/nemotron-3-nano-30b-a3b:free (256K context)

Similar plugs

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…

Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.