Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Kalibr routes AI agent execution paths based on real production telemetry. You define candidate paths (model + tools + parameters) and it learns which performs best for each task, shifting traffic away from failures or degraded providers automatically. Uses Thompson Sampling with 10% canary traffic to catch degradation before users notice.
Unlike LiteLLM or LangChain fallbacks that react to failures after the fact, Kalibr routes proactively based on learned success rates per task, so a degraded provider is avoided before a request is lost.
When to use it
- Automatic failover when OpenAI or Anthropic has an outage
- Routing different agent tasks to different models based on past success rates
- Reducing LLM costs without manually tuning model selection
- Detecting when a model starts returning worse results over time
- Replacing a hardcoded model name with adaptive path selection
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Route my email extraction agent across GPT-4o, Claude, and Gemini and adapt based on what works
- 1Import Router from kalibr and define three candidate paths with different models and parameters
- 2Call router.completion() with the user message, which Kalibr routes to the current best path
- 3Evaluate the response and call router.report(success=True/False) or use success_when= for auto-reporting
- 4Kalibr updates internal telemetry and adjusts path weights after each outcome
- 5After ~50 outcomes, routing is locked in and continuously adapting via canary traffic
Agent calls automatically route to the highest-performing model path, with degraded paths deprioritized without manual intervention
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.