by Luka

A little world
of things I’m building.

Different questions, familiar company.
Choose a project out in the field to hear its story.

Rubrist's human and robot compare judgments at a large table in the foreground. Overclock powers up on the left, Ironside unspools a recording on the right, and smaller Casefile and Dailies scenes sit farther back on the same rocky exoplanet.
Scroll to explore Skip tour

Rubrist

Build AI evaluators and check their judgments against independent human review.

Explore Rubrist

Where to start

Three of these tools form one path: record what your AI did, turn the failures into checks, then decide whether a change can ship. If you have traces already, start with Rubrist. If you install third-party skills, start with Casefile. Each command below installs the tool's plugin in Claude Code; every project page also shows the plain npm or Docker path.

  1. Ironside

    Records what your AI did: inputs, model responses, and tool calls.

    Pre-release · Self-hosted/plugin marketplace add luka-zivkovic/ironside
  2. Rubrist

    Turns failures into evaluators you can check against human judgment.

    Beta · Self-hosted/plugin marketplace add luka-zivkovic/rubrist
  3. Dailies

    Decides whether a change meets your release rules.

    Pre-1.0 · CLI/plugin marketplace add luka-zivkovic/dailies

On their own

  • Casefile

    Inspect a skill before installing it, and notice later changes.

    Pre-1.0 · CLI/plugin marketplace add luka-zivkovic/casefile
  • Overclock

    Skills for coding agents: memory, debugging, review, and evaluation.

    Public toolkit/plugin marketplace add luka-zivkovic/overclock

GitHub