token-optimizer

Overview

Optimize your OpenClaw AI costs with the token-optimizer skill. Slash your expenses from $1,500+/month to under $50/month in just 5 minutes.

Key Features

• Model routing (Haiku by default, Sonnet/Opus only when needed)
• Multi-provider heartbeats (Ollama, LM Studio, Groq, or disable entirely)
• Session management (load 8KB instead of 50KB context)
• Caching (reuse prompts at 10% cost)
• New features: rollback, health check, diff preview, and CI/pipeline friendly output

How It Works

The token-optimizer skill modifies your OpenClaw configuration to optimize costs. It uses model routing, free Ollama heartbeats, prompt caching, and budget controls to reduce expenses.

Use Cases

• Reduce AI costs from $1,500+/month to under $50/month
• Optimize model usage and heartbeats
• Improve session management and caching
• Use rollback, health check, and diff preview features