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
117
工具排名
按实测增长排序，并在不同来源间归一化。 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
aura
MCPAURA is a production-tested SRE agent platform you can deploy in minutes. AURA handles the guardrails, APIs, state management, streaming, and failure handling required to put AI to work safely on production infrastructure.
github实测增长打开来源 ↗
254GitHub 星标-3 (-1.2 %) - 2活跃
🟪 Open-source runtime that ships any LangGraph or Google ADK agent as a production-ready FastAPI service. Bundled , AG-UI copilotkit API, chat UI, 15+ guardrails, MCP, OpenTelemetry, OIDC. One pip install. Self-hosted, no vendor lock-in.
github实测增长打开来源 ↗
安装
git clone https://github.com/Idun-Group/idun-agent-platform ~/.claude/skills/idun-agent-platform198GitHub 星标-1 (-0.50 %) - 3活跃
Self-hosted AI SRE for Kubernetes — zero-instrumentation eBPF observability plus a copilot that fixes issues through guardrailed, self-verifying actions. BYO-LLM, air-gapped capable.
github实测增长打开来源 ↗
131GitHub 星标-4 (-3.0 %) - 4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 %) - 5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 - 6休眠
anti-lie
技能Don't make LLMs honest. Make every factual claim auditable. — An LLM Claim Auditing Layer with T1-T7 truth gradients. 98.1% business effectiveness on LiarBench v0.2.
github实测增长打开来源 ↗
安装
git clone https://github.com/lc198707/anti-lie ~/.claude/skills/anti-lie89GitHub 星标稳定 - 7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-server78GitHub 星标稳定 - 8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 - 9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 %) - 10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 - 11活跃
Make Claude Opus 4.8 behave like Claude Fable 5 — doctrine output style, drift-catching hooks, and an eval loop against golden Fable transcripts. Claude Code plugin.
github实测增长打开来源 ↗
安装
/plugin marketplace add rennf93/opus-fable-playbook33GitHub 星标稳定 - 12休眠
🔍 AI observability skill for Claude Code. Debug LangChain/LangGraph agents by fetching execution traces from LangSmith Studio directly in your terminal.
github实测增长打开来源 ↗
安装
git clone https://github.com/OthmanAdi/langsmith-fetch-skill ~/.claude/skills/langsmith-fetch-skill27GitHub 星标稳定 - 13休眠
astragraph
智能体Policy-enforced observability and fail-closed guardrails for MCP/A2A multi-agent systems.
github实测增长打开来源 ↗
26GitHub 星标稳定 - 14活跃
Sentry instrumentation skill for system-behavior tracking
github实测增长打开来源 ↗
安装
git clone https://github.com/tortastudios/sentry-instrumentation ~/.claude/skills/sentry-instrumentation24GitHub 星标稳定 - 15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 - 16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 - 17活跃
Two Claude Code skills for adversarial code review (single-model PAR and multi-model MMAR with cross-critique to catch hallucinations), plus a fixture-based eval suite.
github实测增长打开来源 ↗
安装
/plugin marketplace add prime-radiant-inc/parallel-adversarial-review17GitHub 星标稳定 - 18活跃
Make Claude write clearly, for everyone.
github实测增长打开来源 ↗
安装
/plugin marketplace add stefanobaghino/simple-output-styles16GitHub 星标稳定 - 19活跃
Claude Code plugin marketplace — agentic-engineering (spec-driven shape→decide→execute→measure→eval with adversarial review) + github-keeper (audit/elevate READMEs and make a repo open-source-ready).
github实测增长打开来源 ↗
安装
/plugin marketplace add GiustoPiedimonte/agentic-engineering-marketplace13GitHub 星标稳定 - 20休眠
A Claude Code skill that adds a rubric-based eval layer to any agent project. Framework-agnostic — generates rubric, test cases, judge prompt, and harness. Returns a weighted score plus a judge-leniency signal.
github实测增长打开来源 ↗
13GitHub 星标稳定 - 21活跃
Query Spanlens LLM observability from Cursor, Claude Desktop, or Continue via MCP.
mcp实测增长打开来源 ↗
安装
claude mcp add mcp-server -- npx @spanlens/mcp-server12GitHub 星标稳定 - 22活跃
bakeoff
技能Turn one decision into a judged tournament of solutions, then pick the best — a Claude Code skill that generates candidates, auto-derives the rubric, judges independently, and returns a defensible winner.
github实测增长打开来源 ↗
安装
/plugin marketplace add CoriChui/bakeoff10GitHub 星标稳定 - 23活跃
galdor
其他A Go-native framework for LLM agents, with OpenTelemetry observability built in.
github实测增长打开来源 ↗
10GitHub 星标稳定
学习与参考资源
按实测增长排序，并在不同来源间归一化。 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 ↗
My complete journey to becoming an Agentic AI Engineer through structured learning, projects, experiments, and production-ready implementations of modern AI systems.
github资源实测增长18GitHub 星标稳定