kalibr
di devonakelley
TransportationSintesi
Ship agents that fix themselves.
Descrizione
Cosa fa questa skill
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.
Quando usarla
- 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
Esempio di workflow
User asks: Route my email extraction agent across GPT-4o, Claude, and Gemini and adapt based on what works
- 1
Import Router from kalibr and define three candidate paths with different models and parameters
- 2
Call router.completion() with the user message, which Kalibr routes to the current best path
- 3
Evaluate the response and call router.report(success=True/False) or use success_when= for auto-reporting
- 4
Kalibr updates internal telemetry and adjusts path weights after each outcome
- 5
After ~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
Requisiti
- KALIBR_API_KEY environment variable
- KALIBR_TENANT_ID environment variable
- Kalibr account at https://dashboard.kalibr.systems/settings
Installazione
clawhub install devonakelley/kalibrEsegui il comando CLI oppure incolla il prompt in Claude Code, Cursor, Codex o nell'agente di coding che usi.