primer-eval is an open-source CLI tool that provides a measurement harness for evaluating the context files used by AI coding agents. It is designed for AI researchers and developers working on agent performance and benchmarking.
primer-eval sits in PulseGate's LLM eval & observability category. It focuses on enabling measurement and evaluation of AI coding agent context files for improved agent performance. It is built as an open-source project for AI researchers. primer-eval is open source under the MIT license. primer-eval is available on the command line.
Behind primer-eval is kanwa2006, and the product first shipped in 2026. Development happens publicly on GitHub with 53 commits in the last 90 days. PulseGate's similarity index finds few close equivalents — primer-eval occupies a relatively distinct niche. Key capabilities include AI agent evaluation, context file measurement, and command-line interface.
Latest indexed changes and source events
primer-eval discovered by the PulseGate indexer
Other apps tracked under the same category.
