Aller au contenu
TakoAPI
Retour aux skills

kalibr

par devonakelley

Transportation
—Pas encore noté
Ta note

Résumé

Ship agents that fix themselves.

Description

Ce que fait ce 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.

Quand l'utiliser

  • 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

Exemple de workflow

ENTRÉE

User asks: Route my email extraction agent across GPT-4o, Claude, and Gemini and adapt based on what works

AGENT
  1. 1

    Import Router from kalibr and define three candidate paths with different models and parameters

  2. 2

    Call router.completion() with the user message, which Kalibr routes to the current best path

  3. 3

    Evaluate the response and call router.report(success=True/False) or use success_when= for auto-reporting

  4. 4

    Kalibr updates internal telemetry and adjusts path weights after each outcome

  5. 5

    After ~50 outcomes, routing is locked in and continuously adapting via canary traffic

SORTIE

Agent calls automatically route to the highest-performing model path, with degraded paths deprioritized without manual intervention

Prérequis

  • KALIBR_API_KEY environment variable
  • KALIBR_TENANT_ID environment variable
  • Kalibr account at https://dashboard.kalibr.systems/settings

Installation

clawhub install devonakelley/kalibr

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens