Benchmark Projects
A collection of projects that are used to benchmark the performance of Agent Zero.
README
Benchmark Projects
Benchmark Projects creates standard Agent Zero projects from a bundled benchmark template, launches hidden benchmark runs from the plugin dashboard, and stores run artifacts inside each created project.
Highlights
- creates benchmark-ready projects under
usr/projects/ - keeps benchmark orchestration in the plugin, not in agent-visible tools
- launches one task chat per task with an isolated working directory
- stores results under
benchmark_runs/<run_id>/ - compares runs within the same project
Bundled Benchmark
V1 ships with one bundled benchmark preset: project_b.