Store

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

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

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