Five projects. One studio.

A human-in-the-loop measurement family and a pair of developer tools. Each ships independently, and each repo carries its own verification story.

5 projects · 3 measurement · 2 tooling

Human-in-the-loop measurement

3 projects

Three projects, one loop: HITL Kit renders the gate, eval-kit measures it, tag-kit calibrates the humans doing the measuring.

HITL Kit
Twenty React primitives for the moment an agent hands control to a person: interrupts, approvals, evidence, and provenance.
MeasurementDeployed at hitlkit.dev · every primitive installs individually via the shadcn CLI · copy, paste, own.
eval-kit
Scores whether your agent respects human authority: stops when it must, asks when it should, never averaged into one number.
MeasurementThe gates release · mandated compliance and discretionary precision/recall scored from the trace, never averaged · three reference suites · four adapters (anthropic, openai, http, mock) · file-based, single-user, not a hosted service.
tag-kit
Structured tagging primitives for human-in-the-loop annotation: scoped tags you can aggregate and score, not free-text labels.
Measurement@tag-kit/core (zero runtime deps) · @tag-kit/ui (headless React) · extracted from a real moderation app (inertial).

Developer tooling

2 projects

Separate work, same standards. These serve the building of software, not the measurement thesis.