harness-bench-fast provides a standardized, self-contained benchmark with 298 tasks covering file operations, code editing, CSV/SQLite/XLSX data pipelines, memory management, and other agentic scenarios. It is designed for rigorous evaluation of AI agents and frameworks such as LangChain. The package is open source under the MIT license and available on PyPI and GitHub.
In the Agent evaluation & testing space, harness-bench-fast takes a focused approach. It focuses on evaluating and comparing the performance of AI agents on realistic software engineering and data tasks. harness-bench-fast is an open-source project aimed at AI researchers and developers. The project is open source (MIT). It ships for the command line.
ai-forever builds and maintains harness-bench-fast, and it first shipped in 2026. The project is developed in the open on GitHub with 37 stars and 76 commits in the last 90 days. Among its 5 catalogued features are Agent Benchmark, File Operations, and Code Editing.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do