
Open-source evaluation harness for autonomous coding agents that measures cost per successful task, cache economics, and risk-aware routing using isolated worktrees and holdout tests. Includes an MCP plugin for Claude Code.
Prices and medians update for the tier you select. Caution: thin market — treat statistics as indicative.
Ranked by how closely each one matches Agent FinOps Sandbox's job. Prices show each provider's Pro state; entry prices are labelled as such. Unpriced products still belong to the market.
Thin market — few comparable priced products; treat statistics as indicative.