简介
Evidently 是一个拥有 7,300+ GitHub stars 的开源 ML/LLM 可观测性框架,提供 100+ 内置指标用于评估、测试和监控 AI 系统。覆盖数据漂移检测、模型质量和 LLM 输出监控。
Evaluate, test, and monitor AI systems with 100+ built-in metrics for data drift, model quality, and LLM output. 7.3K+ stars.
这里应该同时让用户和 Agent 知道第一步该复制什么、安装什么、落到哪里。
pip install evidentlyfrom evidently.report import Report
from evidently.metric_preset import TextEvals
report = Report(metrics=[TextEvals()])
report.run(current_data=data)
report.save_html("report.html")Evidently 是一个拥有 7,300+ GitHub stars 的开源 ML/LLM 可观测性框架,提供 100+ 内置指标用于评估、测试和监控 AI 系统。覆盖数据漂移检测、模型质量和 LLM 输出监控。
Created by Evidently AI. Licensed under Apache-2.0.
evidently — ⭐ 7,300+
Open-source platform for building, evaluating, and monitoring AI agents in production. Observability, prompt playground, LLM-as-judge evals, experiment comparison. LGPL-3.0, 4,000+ stars.
Open-source Jira/Linear alternative with AI-powered pages. Issues, sprints, modules, roadmaps, and real-time analytics. Self-hostable via Docker. AGPL-3.0, 47,500+ stars.
Modern open-source CRM with AI features. Custom objects, kanban views, email sync, workflow automation. NestJS + React + PostgreSQL. AGPL-3.0, 43,700+ stars.