| name | token-optimizer |
| description | Reduce OpenClaw AI costs by 97%. Haiku model routing, free Ollama heartbeats, prompt caching, and budget controls. Go from $1,500/month to $50/month in 5 minutes. |
| homepage | https://github.com/smartpeopleconnected/openclaw-token-optimizer |
| triggers | ["high costs","expensive","burning tokens","reduce costs","save money","budget exceeded","token optimization"] |
🦞 Token Optimizer for OpenClaw
Slash your AI costs from $1,500+/month to under $50/month.
The Problem
OpenClaw defaults prioritize capability over cost. You're burning expensive Sonnet/Opus tokens on tasks Haiku handles perfectly, paying for API heartbeats that could run free locally, and loading 50KB of context when 8KB suffices.
The Solution
Four optimizations that work together:
✅ Model Routing (92% savings)
Haiku by default, Sonnet/Opus only when needed
✅ Ollama Heartbeats (100% savings)
Free local LLM for status checks
✅ Session Management (80% savings)
Load 8KB instead of 50KB context
✅ Prompt Caching (90% savings)
Reuse system prompts at 10% cost
Cost Comparison
| Period | Before | After |
|---|
| Daily | $2-3 | $0.10 |
| Monthly | $70-90 | $3-5 |
| Yearly | $800+ | $40-60 |
What's Included
- One-command optimizer
- Ready-to-use config templates
- SOUL.md & USER.md templates
- System prompt optimization rules
- Verification tools
- Windows + Unix installers
Quick Start
clawhub install token-optimizer
python src/analyzer.py
python src/optimizer.py --mode full
python src/verify.py
Configuration Generated
{
"agents": {
"defaults": {
"model": { "primary": "anthropic/claude-haiku-4-5" },
"cache": { "enabled": true, "ttl": "5m" }
}
},
"heartbeat": {
"model": "ollama/llama3.2:3b"
},
"budgets": {
"daily": 5.00,
"monthly": 200.00
}
}
Links
Author
Smart People Connected
License
MIT License - Free to use, modify, and distribute.
5 minutes to setup. 97% cost reduction. Stop burning tokens. Start building.
