工具说明为英文。
LLM 可观测性
LLM 应用的监控、追踪、评估和质量管理。
用途
活跃度
排序方式
76
工具排名
Ranked by normalized popularity across sources. 原始值保留各自的数据窗口;计算变化需要 7 天内至少两次测量。
- 1活跃
agent-kernel
智能体The Operating System for Scalable Enterprise AI Agents - Run, orchestrate, and deploy Compliant Enterprise AI Agents at scale across frameworks, without lock-in, rewrites or fragile glue code. Native support for MCP, A2A. Interface with all…
github实测增长打开来源 ↗
166GitHub 星标+29 (+21.2 %) - 2活跃
VeriRun
其他Evidence-first infrastructure for reproducible, isolated executable evaluation and online rewards.
github实测增长打开来源 ↗
163GitHub 星标+47 (+40.5 %) - 3活跃
Research-backed, eval-driven skills for AI agents
github实测增长打开来源 ↗
安装
git clone https://github.com/ZSeven-W/craft-skills ~/.claude/skills/craft-skills145GitHub 星标+14 (+10.7 %) - 4活跃
Skills, prompts, and instructions for building AI agents on top of Dynatrace production context
github实测增长打开来源 ↗
安装
git clone https://github.com/Dynatrace/dynatrace-for-ai ~/.claude/skills/dynatrace-for-ai135GitHub 星标+4 (+3.1 %) - 5活跃
🐙 ADLC Team Skills — Agentic SDLC for Engineering Teams
github实测增长打开来源 ↗
安装
git clone https://github.com/tikalk/adlc-team-skills ~/.claude/skills/adlc-team-skills132GitHub 星标+1 (+0.76 %) - 6活跃
74 open-source Agent Skills for Claude Code and Codex: AI SEO, AEO and GEO, code review with an A-F ship grade, CI gates, AI evals, design systems, conversion copy, Instagram growth, iOS and Android app shipping, creator rights, and…
github实测增长打开来源 ↗
129GitHub 星标-4 (-3.0 %) - 7活跃
langfuse-mcp
MCPA Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability
github实测增长打开来源 ↗
105GitHub 星标稳定 - 8105GitHub 星标+1 (+0.96 %)
- 9活跃
Vendor-neutral OpenTelemetry skills for AI coding agents, grounded in upstream sources
github实测增长打开来源 ↗
安装
git clone https://github.com/ollygarden/opentelemetry-agent-skills ~/.claude/skills/opentelemetry-agent-skills97GitHub 星标+1 (+1.0 %) - 10活跃
MCP server for Langfuse LLM observability — trace and observation analysis.
mcp实测增长打开来源 ↗
安装
claude mcp add langfuse -- npx langfuse-observability-mcp-server80GitHub 星标+2 (+2.6 %) - 11活跃
local-first analytics for AI agent skills
github实测增长打开来源 ↗
安装
git clone https://github.com/crafter-station/skill-kit ~/.claude/skills/skill-kit77GitHub 星标+1 (+1.3 %) - 12活跃
Deletion-first Agent Skill for removing test bloat, verification theater, and speculative fallbacks while preserving behavior.
github实测增长打开来源 ↗
安装
git clone https://github.com/MrZoyo/deslop-GPT ~/.claude/skills/deslop-GPT76GitHub 星标+48 (+171.4 %) - 13活跃
Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters
github实测增长打开来源 ↗
安装
git clone https://github.com/adewale/skill-eval-harness ~/.claude/skills/skill-eval-harness73GitHub 星标+4 (+5.8 %) - 14活跃
AgentX python SDK. Build multi-agent AI workforce. Run evaluation. Trace your agent. Full Observability.
github实测增长打开来源 ↗
68GitHub 星标稳定 - 15活跃
Open benchmark for Claude Code SEO skills — real headless execution against fixture sites with planted-defect answer keys. Deterministic scoring, pre-registered rubric.
github实测增长打开来源 ↗
安装
git clone https://github.com/aleclindz/seo-skill-bench ~/.claude/skills/seo-skill-bench51GitHub 星标-5 (-8.9 %) - 16活跃
nora
MCPOpen-source, self-hosted control plane for OpenClaw and Hermes AI-agent fleets on Docker/Kubernetes — REST, CLI, and MCP.
github实测增长打开来源 ↗
50GitHub 星标+2 (+4.2 %) - 17活跃
Agent skills for Arize — datasets, experiments, and traces via the ax CLI
github实测增长打开来源 ↗
安装
git clone https://github.com/Arize-ai/arize-skills ~/.claude/skills/arize-skills47GitHub 星标稳定 - 18活跃
cap-evolve
MCPOptimize any AI agent’s skills, tools/MCP, and prompts against your own evals.
github估算动量打开来源 ↗
47GitHub 星标— - 19活跃
Mini Program Engineering Skill Suite is an Agent Skill suite for evidence‑first mini‑program development. It helps agents bring WeChat or other mini‑program projects from vague intent to reliable engineering work: project intake, product…
github实测增长打开来源 ↗
安装
git clone https://github.com/NocodeMrLi/mini-program-engineering-skill-suite ~/.claude/skills/mini-program-engineering-skill-suite43GitHub 星标+4 (+10.3 %) - 20活跃
Real-time execution trace and cost intelligence for Claude Code
github实测增长打开来源 ↗
安装
/plugin marketplace add DeibyGS/claudestat34GitHub 星标稳定 - 21活跃
Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.
github实测增长打开来源 ↗
22GitHub 星标+2 (+10.0 %) - 22活跃
untell
其他AI-detector auditing toolkit: measures how often a detector flags genuine human writing, how stable its verdict is across seeds, and whether that verdict survives meaning-preserving edits. Detector-in-the-loop measurement harness. Claude…
github实测增长打开来源 ↗
18GitHub 星标稳定 - 23活跃
rashomon
技能Measure prompt and skill improvements with blind A/B comparison.
github实测增长打开来源 ↗
安装
/plugin marketplace add shinpr/rashomon18GitHub 星标稳定
学习与参考资源
Ranked by normalized popularity across sources. 这些资源可单独访问,不参与主要排名。
- 1活跃打开来源 ↗
Curated + scored map of official MCP servers and agents for DevOps, Cloud, SRE, and Platform Engineering — every entry rated on production access, approval gates, and audit evidence.
github资源实测增长77GitHub 星标稳定 - 2活跃打开来源 ↗
50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.
github安装
资源实测增长git clone https://github.com/ContextJet-ai/awesome-llm-observability ~/.claude/skills/awesome-llm-observability33GitHub 星标+3 (+10.0 %)