Playground for reproducible Harbor eval tasks that test local coding agents with offline, Docker-backed verifiers.
-
Updated
Jul 4, 2026 - Python
#
harbor-framework
Here are 3 public repositories matching this topic...
Adversarial probes for Harbor benchmark integrity. Ocarina Labs' Harbor extension — null-agent, output-echo, judge-injection, and verifier-tamper probes that flag broken benchmarks before they ship.
-
Updated
Apr 24, 2026 - Python
Terminal-Bench evals using your own Pi agent
-
Updated
Jul 4, 2026 - Python
Improve this page
Add a description, image, and links to the harbor-framework topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the harbor-framework topic, visit your repo's landing page and select "manage topics."