The first open-source effort estimation tool built for AI coding agents. PERT + METR + wave planning.
-
Updated
Oct 26, 2026 - Python
The first open-source effort estimation tool built for AI coding agents. PERT + METR + wave planning.
Item-response analysis of METR's AI time horizons, and HorizonCAT: cost-aware adaptive measurement of frontier agents
Reproducible coding-agent evaluations with METR Hawk and Inspect: real traces, behavioral checks, monitoring, and latency measurements.
Interactive visualization of METR AI agent time horizon benchmark with exponential projections at 3, 6, 12, 18, 24, and 36 months. Tracks p50/p80 task-completion horizons across 22 frontier models (2019-2026).
Exploratory pilot: how much METR's Time Horizon 1.1 results rest on estimated rather than measured human task times. Not affiliated with METR.
To associate your repository with the metr topic, visit your repo's landing page and select "manage topics."