Pinned Loading

1. agent-eval-starter agent-eval-starter Public

   Make an LLM agent's reliability measurable: a vendor-neutral reference wiring an agent to OpenTelemetry tracing, an eval harness, and guardrails — with evals running as a CI gate. Runs offline, zer…

   Python 3

2. git-habits git-habits Public

   Measure refactoring, duplication and churn from your own git history. Compare any two periods — for example, before and after your team adopted AI coding tools. Runs entirely locally; no code leave…

   Python 1

3. diff-habits diff-habits Public

   Python 1

4. resumable-llm-pipeline resumable-llm-pipeline Public

   A resumable, idempotent, cost-aware LLM pipeline — instrumented, with a local-vs-cloud economics benchmark. Kill it and resume, no re-spend.

   Python 3