token-saver

Overview
Reduce OpenClaw AI costs with model-aware optimization. Token Saver v3 adapts to your model’s context window, providing dynamic compaction presets and robust model detection with fallback.

Key Features

• Model-aware optimization for reduced costs
• Dynamic compaction presets based on your model’s context window
• Robust model detection with fallback
• Intelligent file compression

How It Works
Token Saver v3 analyzes your workspace files and model context window to provide optimized compaction presets and detect your model. It then applies these presets to compress your files and reduce costs.

Use Cases

• Reduce OpenClaw AI costs by optimizing compaction presets
• Improve model detection and fallback for robust performance
• Enhance file compression for efficient token usage

Commands

• /optimize — Full dashboard — files, models, context usage %
• /optimize tokens — Compress workspace files (auto-backup)
• /optimize compaction — Chat compaction control (model-aware)
• /optimize compaction balanced — Apply balanced preset (60% of context)
• /optimize compaction 120 — Custom threshold (compact at 120K)
• /optimize models — Detailed model audit with registry
• /optimize revert — Restore backups, disable persistent mode