Agent 评测+规则包——更安全上线

Agent Evaluation is a Python framework that runs repeatable, scored tests for virtual agents, so teams can catch regressions automatically in CI.

Microsoft AI Agent Evals is a GitHub Action that runs offline agent evaluations in CI/CD using datasets and evaluators so PRs ship with measurable gates.

Margin Eval is an eval runtime that benchmarks CLI coding agents and records accuracy, token usage, runtime, and traces in a reproducible format.

AgentEval is a .NET evaluation toolkit for AI agents that validates tool usage, scores RAG quality, compares models, and exports regression-ready reports.

RuleForge is a CLI that scans a repo and generates rule files (CLAUDE.md, .cursorrules, Copilot instructions) so agents follow consistent boundaries.

Awesome Cursor Rules (ZH) is a bilingual .cursorrules library that helps Cursor users enforce architecture, security, and style constraints across a repo.