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

75

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. 1

    技能
    活跃

    Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.

    Python许可证: Apache-2.0
    • agent-evaluation
    • agent-security
    • agent-skills
    • agentic-ai
    • benchmark

    github实测增长打开来源 ↗

    安装 git clone https://github.com/NVIDIA/SkillEvaluator ~/.claude/skills/SkillEvaluator

    399GitHub 星标+51 (+14.7 %)
  2. 2

    技能
    活跃

    Anchor — the production-grade AGENTS.md template for AI coding agents. 51 sections of battle-tested rules. Keep your agents grounded.

    许可证: MIT
    • agent-instructions
    • agents-md
    • ai-agent-instructions
    • ai-coding
    • ai-coding-agent

    github实测增长打开来源 ↗

    安装 git clone https://github.com/peva3/anchor ~/.claude/skills/anchor

    8GitHub 星标稳定
  3. 3

    其他
    活跃

    A Go-native framework for LLM agents, with OpenTelemetry observability built in.

    Go许可证: Apache-2.0
    • a2a
    • agents
    • ai
    • anthropic
    • bedrock

    github实测增长打开来源 ↗

    10GitHub 星标稳定
  4. 4

    MCP
    活跃

    Architecture-first Python scaffold for an auditable multi-agent corporate credit desk using A2A, MCP, deterministic credit policies, model routing, and OpenTelemetry.

    Python
    • a2a-protocol
    • agentic-ai
    • auditability
    • clean-architecture
    • credit-risk

    github实测增长打开来源 ↗

    0GitHub 星标稳定
  5. 5

    技能
    活跃

    Dashboard for monitoring claude code sessions.

    Python许可证: Apache-2.0
    • agents
    • agentskills
    • claude-code
    • claude-code-plugin
    • claude-code-skills

    github实测增长打开来源 ↗

    安装 /plugin marketplace add JayantDevkar/claude-code-karma

    323GitHub 星标+2 (+0.62 %)
  6. 6

    MCP
    活跃

    AURA 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.

    Rust许可证: Apache-2.0
    • a2a
    • ai-agent-framework
    • ai-agents
    • ai-sre
    • aiops

    github实测增长打开来源 ↗

    291GitHub 星标+33 (+12.8 %)
  7. 7

    技能
    活跃

    Marketing Mix Model expert agent plugin for Claude Code - pymc-marketing v0.18.2+

    Python
    • claude-code-agent
    • claude-code-plugin
    • claude-code-skill
    • data-analysis
    • data-analytics

    github实测增长打开来源 ↗

    安装 /plugin marketplace add Yakoub-ai/agent-mmm

    4GitHub 星标稳定
  8. 8

    技能
    活跃

    🪢 Langfuse documentation -- Langfuse is the open source LLM Engineering Platform. Observability, evals, prompt management, playground and metrics to debug and improve LLM apps

    MDX许可证: MIT
    • agent-skills
    • agents
    • genai
    • hacktoberfest
    • langfuse

    github实测增长打开来源 ↗

    安装 git clone https://github.com/langfuse/langfuse-docs ~/.claude/skills/langfuse-docs

    239GitHub 星标+3 (+1.3 %)
  9. 9

    技能
    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.

    Python许可证: GPL-3.0
    • a2a-protocol
    • ag-ui-protocol
    • agent-platform
    • agentic-ai
    • agents

    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-platform

    199GitHub 星标稳定
  10. 10

    技能
    活跃

    YAO = Yielding AI Outcomes. A rigorous engineering, evaluation, governance, and portability system for reusable agent skills.

    Python许可证: MIT
    • agent-skills
    • ai-agents
    • evaluation
    • governance
    • meta-skill

    github实测增长打开来源 ↗

    安装 git clone https://github.com/yaojingang/yao-meta-skill ~/.claude/skills/yao-meta-skill

    2 589GitHub 星标+38 (+1.5 %)
  11. 11

    智能体
    活跃

    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…

    Python许可证: Apache-2.0
    • a2a
    • adk
    • ai-agents
    • aws
    • azure

    github实测增长打开来源 ↗

    166GitHub 星标+29 (+21.2 %)
  12. 12

    技能
    活跃

    Research-backed, eval-driven skills for AI agents

    Python许可证: Apache-2.0
    • agent-skills
    • ai-agents
    • codex
    • design
    • evals

    github实测增长打开来源 ↗

    安装 git clone https://github.com/ZSeven-W/craft-skills ~/.claude/skills/craft-skills

    145GitHub 星标+14 (+10.7 %)
  13. 13

    MCP
    活跃

    Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.

    Python许可证: MIT

      mcp实测增长打开来源 ↗

      安装 claude mcp add ai-guardian -- uvx ai-guardian-aiops

      0GitHub 星标稳定
    • 14

      技能
      活跃

      Skills, prompts, and instructions for building AI agents on top of Dynatrace production context

      JavaScript许可证: Apache-2.0
      • agent-skills
      • ai-agents
      • claude-code
      • devops
      • dql

      github实测增长打开来源 ↗

      安装 git clone https://github.com/Dynatrace/dynatrace-for-ai ~/.claude/skills/dynatrace-for-ai

      135GitHub 星标+4 (+3.1 %)
    • 15

      智能体
      活跃

      Local-first control plane for durable, governed agent teams: DAG orchestration, approvals, memory, signed skills, trace contracts, and realtime.

      Python许可证: Apache-2.0
      • a2a-protocol
      • agentic-ai
      • ai-agents
      • fastapi
      • llmops

      github实测增长打开来源 ↗

      0GitHub 星标稳定
    • 16

      MCP
      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…

      JavaScript许可证: MIT
      • agent-orchestration
      • agent-skill
      • agent-skills
      • ai-agents
      • ai-coding

      github实测增长打开来源 ↗

      129GitHub 星标-4 (-3.0 %)
    • 17

      技能
      活跃

      🐙 ADLC Team Skills — Agentic SDLC for Engineering Teams

      Shell许可证: MIT
      • adr
      • agent-skills
      • agentic-sdlc
      • ai-coding
      • developer-tools

      github实测增长打开来源 ↗

      安装 git clone https://github.com/tikalk/adlc-team-skills ~/.claude/skills/adlc-team-skills

      132GitHub 星标+1 (+0.76 %)
    • 18

      MCP
      活跃

      A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability

      Python许可证: MIT
      • agent-skills
      • ai-agents
      • claude-code
      • codex
      • developer-tools

      github实测增长打开来源 ↗

      105GitHub 星标稳定
    • 19

      MCP
      活跃

      Self improving agents through iterations

      Python许可证: Apache-2.0
      • agent-learning
      • agent-memory
      • agentic-workflows
      • ai-agents
      • claude-code

      github实测增长打开来源 ↗

      105GitHub 星标+1 (+0.96 %)
    • 20

      技能
      活跃

      Vendor-neutral OpenTelemetry skills for AI coding agents, grounded in upstream sources

      Shell许可证: Apache-2.0
      • agent-skills
      • ai
      • observability
      • opentelemetry

      github实测增长打开来源 ↗

      安装 git clone https://github.com/ollygarden/opentelemetry-agent-skills ~/.claude/skills/opentelemetry-agent-skills

      97GitHub 星标+1 (+1.0 %)
    • 21

      MCP
      活跃

      MCP server for Langfuse LLM observability — trace and observation analysis.

      TypeScript许可证: MIT

        mcp实测增长打开来源 ↗

        安装 claude mcp add langfuse -- npx langfuse-observability-mcp-server

        80GitHub 星标+2 (+2.6 %)
      • 22

        智能体
        活跃

        Deterministic crash tests for agent control planes: paired worlds, hard stops, budgets, scopes, approvals, and hash-linked receipts.

        TypeScript许可证: Apache-2.0
        • a2a
        • agent-evaluation
        • ai-agents
        • benchmark
        • deterministic-replay

        github实测增长打开来源 ↗

        1GitHub 星标稳定
      • 23

        MCP
        活跃

        A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.

        Go许可证: Apache-2.0
        • a2a
        • a2a-protocol
        • ag-ui
        • agent
        • agent-framework

        github实测增长打开来源 ↗

        1 763GitHub 星标+16 (+0.92 %)
      • 24

        技能
        活跃

        Glanceable Claude Code and Codex state in your terminal tabs: white=idle, blue=working, orange=waiting. Multi-terminal (iTerm2, WezTerm, AI Power Term), a live status bar with Anthropic usage limits, /sfl and /nil window save-and-restore,…

        Shell许可证: MIT
        • ai-workflow-observability
        • claude-code
        • claude-code-hooks
        • claude-code-skill
        • claude-code-skills

        github实测增长打开来源 ↗

        安装 git clone https://github.com/wasulajr/headsup ~/.claude/skills/headsup

        1GitHub 星标稳定
      • 25

        技能
        活跃

        local-first analytics for AI agent skills

        TypeScript
        • agent-skills
        • analytics
        • bun
        • claude-code
        • cli

        github实测增长打开来源 ↗

        安装 git clone https://github.com/crafter-station/skill-kit ~/.claude/skills/skill-kit

        77GitHub 星标+1 (+1.3 %)