harbor: evaluate agents in sandboxed environments

www.harborframework.com · 2026-10-05 · by Long Nguyen ·generic
A framework for evaluating and optimizing sandboxed agents and models.

harbor: evaluate agents in sandboxed environments

harbor: evaluate agents in sandboxed environments

harbor is a framework for specifying sandboxed agent tasks for evaluation and optimization

uv tool install harbor

Read the docs

from the makers of terminal-bench

see harbor in action

Comments (0)

No comments yet