Store

Local-first evaluation dashboard for agent CLIs with deterministic graders, live trace telemetry, and accuracy audits. https://github.com/RasputinKaiser/OpenEval

Free, local-first evaluation dashboard for agent CLIs with cross-harness transcript collection, live trace intelligence, deterministic graders, and accuracy audits.

OpenAI Codex CLI with --dangerously-bypass-approvals-and-sandbox