tokenoptimizer
smartpeopleconnected द्वारा
Coding Agents & IDEsसंक्षिप्त
Reduce OpenClaw AI costs by 97%.
विवरण
यह स्किल क्या करती है
Routes OpenClaw agent requests to Haiku by default, escalating to Sonnet or Opus only when needed. Offloads heartbeat checks to local providers like Ollama or free tiers like Groq, reduces session context from ~50KB to ~8KB, and caches repeated prompts at 10% of standard cost. All changes write to ~/.openclaw/ with automatic backups.
Every change runs in dry-run mode by default, creates timestamped backups before writing, and produces a verification report after applying, so there is no guesswork about what changed or whether it worked.
इसे कब इस्तेमाल करें
- Cutting a $1,500/month AI bill down to under $50
- Running heartbeat checks locally with Ollama instead of paying per token
- Previewing config changes in dry-run mode before applying them to a live setup
- Rolling back to a previous config after an optimization breaks agent behavior
- Setting daily and monthly token budget caps to avoid unexpected charges
उदाहरण वर्कफ़्लो
User asks: optimize my OpenClaw setup to reduce API costs
- 1
Runs
python cli.py analyzeto inspect current model routing, heartbeat config, and context load - 2
Runs
python cli.py optimizein dry-run mode to generate a diff of proposed changes - 3
User confirms and runs
python cli.py optimize --applyto write the config - 4
Runs
python cli.py setup-heartbeat --provider ollama --applyto route heartbeats to a local model - 5
Runs
python cli.py verifyto confirm the new config and view projected savings
OpenClaw config updated with Haiku as default model, Ollama handling heartbeats, 8KB session context, and prompt caching enabled, with a backup created and a savings report generated
इंस्टॉलेशन
clawhub install smartpeopleconnected/tokenoptimizerCLI कमांड चलाएँ, या प्रॉम्प्ट को Claude Code, Cursor, Codex या जो भी कोडिंग एजेंट आप इस्तेमाल करते हैं उसमें पेस्ट करें।