Skip to content
#

research-preview

Here are 10 public repositories matching this topic...

An evidence-bound Harness-of-Harness for verifiable long-horizon agent development. Pre-registered matched-budget benchmark against a plain agent (the harness does not win it), falsifier-checked release gates, and every published number anchored to a claims ledger — including the findings that do not flatter it.

  • Updated Sep 15, 2026
  • Python

Add this topic to your repo

To associate your repository with the research-preview topic, visit your repo's landing page and select "manage topics."

Learn more