Pinned Loading

1. synthetic-code synthetic-code Public

   Implementación de referencia para el libro Código Sintético, contiene patrones de producción para sistemas multiagente (orquestación eficiente, calidad autónoma en CI/CD, código autolimpiable y arq…

   Python

2. kafka-agent-citizen kafka-agent-citizen Public

   The agent as a citizen of the log. An AI review agent that consumes and produces events instead of being called — with the four doctrines that keep it honest: partition key, idempotency, schema-as-…

   Java

3. agent-otel-tracing agent-otel-tracing Public

   The ReAct loop is a trace. Instrument an AI agent as a distributed trace and read its synthetic signals — tokens, cache hit rate, iterations, tool errors, latency — straight from the spans.

   Python

4. ciu-tracker ciu-tracker Public

   Cost per Useful Iteration (CIU) — measure the real cost of running AI agents in production.

   Python

5. eval-harness-minimal eval-harness-minimal Public

   LLM-as-judge without self-deception. The agentic testing pyramid: free deterministic checks first, an LLM judge second, cost reported beside quality — always.

   Python

6. llm-port-java-node llm-port-java-node Public

   The model is a detail. A Clean Architecture port for LLM-backed use cases, with swappable adapters in Java and Node.js/TypeScript.

   Java