Laboratorio de ingeniería · Galicia

Lab34 estudia cómo llevar la IA a las operaciones IT de forma que quien las opera pueda auditarla, mantenerla y apagarla.

Publica lo que aprende: informes con sus fuentes, herramientas con su código y notas de trabajo sin pulir. Este registro es todo lo que hay.

Registro Actualizado
  1. L34-A-003
    ronsel

    Workflows y automatizaciones end-to-end declarativos y resilientes para todo el equipo.

    Artefacto Open source
  2. L34-N-008
    ronsel: E2E Flows You Can Read, Run and Commit

    flows has grown up and changed its name. ronsel turns end-to-end tests into Markdown documents: prose and executable steps in the same file, run from a notebook-style UI, the CLI or your pipeline.

    Nota Publicado
  3. L34-A-001
    redact

    Detecta datos sensibles en repositorios antes de que lleguen a un LLM.

    Artefacto Open source
  4. L34-N-006
    Technical guardrails for LLM-assisted code: the full catalog

    A defense-in-depth reference for Node/NestJS teams: nine layers of automated guardrails, from agent hooks and compiler strictness to CI gates and runtime rollback, each one catching what the previous one missed.

    Nota Publicado
  5. L34-N-007
    redact, Rewritten in Go: One Binary, a TUI, and Reproducible Scans

    The new version of redact ships as a single static Go binary with an interactive TUI and a headless CLI. Same two scanners, plus persisted, reproducible results -- and no Python to set up.

    Nota Publicado
  6. L34-R-001
    More code, less confidence

    What DORA 2025, GitClear, LinearB and Stack Overflow data say about why scrum teams ship worse code — and the habits of the teams that don't.

    Informe Publicado
  7. L34-N-005
    One review, three tiers: a feature delivery workflow that scales its own overhead

    From business story to development without the queue: a swimlane workflow where architecture, contracts and infrastructure are checked once, asynchronously, and infra never sits on the critical path. Block by block, with a worked example and the sources it comes from.

    Nota Publicado
  8. L34-N-004
    redact: Find Sensitive Data in Your Repos Before It Reaches an LLM

    An open-source tool that scans repositories for secrets, credentials, and PII using regex patterns and local LLM analysis, helping you build guardrail lists before sending code to an AI.

    Nota Publicado
  9. L34-A-002
    proxy

    Un gateway abierto para asegurar y controlar el uso de IA en una organización: qué datos salen, quién usa qué y cuánto cuesta.

    Artefacto Open source
  10. L34-N-003
    proxy: An Open-Source Gateway to Secure and Control Your AI Usage

    An OpenAI-compatible reverse proxy that manages credentials, enforces rate limits, tracks token usage, and applies content guardrails for LLM API requests.

    Nota Publicado
  11. L34-N-002
    The 5 Slides Generative AI Theoretical Training Course

    A concise theoretical training course on generative AI, condensed into 5 key slides. Delivered for a customer in India.

    Nota Publicado
  12. L34-N-001
    flows: Resilient and Declarative E2E Workflows and automation

    Simple YAML files for complex E2E flows testing.

    Nota Publicado