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

121

工具排名

Ranked by known GitHub stars, highest first; archived repositories come after maintained repositories. 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

    Real-time execution trace and cost intelligence for Claude Code

    TypeScript许可证: MIT
    • agentic-workflow
    • ai-productivity
    • anthropic
    • anthropic-claude
    • claude

    github实测增长打开来源 ↗

    安装 /plugin marketplace add DeibyGS/claudestat

    34GitHub 星标稳定
  2. 2

    技能
    休眠

    🔍 AI observability skill for Claude Code. Debug LangChain/LangGraph agents by fetching execution traces from LangSmith Studio directly in your terminal.

    许可证: MIT
    • agent-debugging
    • ai-agents
    • claude-skills
    • claude-skills-creator
    • claude-skills-hub

    github实测增长打开来源 ↗

    安装 git clone https://github.com/OthmanAdi/langsmith-fetch-skill ~/.claude/skills/langsmith-fetch-skill

    27GitHub 星标稳定
  3. 3

    智能体
    休眠

    Policy-enforced observability and fail-closed guardrails for MCP/A2A multi-agent systems.

    Rust
    • a2a
    • ai-agents
    • llm-security
    • mcp
    • multi-agent

    github实测增长打开来源 ↗

    26GitHub 星标稳定
  4. 4

    技能
    活跃

    Sentry instrumentation skill for system-behavior tracking

    Shell许可证: MIT
    • agent-skills
    • claude-skills
    • codex-skill
    • instrumentation
    • monitoring

    github实测增长打开来源 ↗

    安装 git clone https://github.com/tortastudios/sentry-instrumentation ~/.claude/skills/sentry-instrumentation

    24GitHub 星标稳定
  5. 5

    MCP
    活跃

    Log Claude Code sessions to Opik, the open-source LLM observability and evaluation platform, built by Comet. Tracing, evaluation, and skills for observable AI applications.

    Go许可证: Apache-2.0
    • ai-agent
    • claude-ai
    • claude-code-plugin
    • llm-observation
    • mcp-server

    github实测增长打开来源 ↗

    22GitHub 星标+1 (+4.8 %)
  6. 6

    MCP
    活跃

    Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.

    HTML许可证: MIT
    • agent-monitoring
    • agentic-ai
    • ai-agents
    • ai-engineering
    • audit

    github实测增长打开来源 ↗

    22GitHub 星标稳定
  7. 7

    其他
    活跃

    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…

    Python许可证: MIT
    • ai-detection
    • ai-detector
    • benchmark
    • claude-code
    • claude-code-skill

    github实测增长打开来源 ↗

    18GitHub 星标-1 (-5.3 %)
  8. 8

    技能
    活跃

    Measure prompt and skill improvements with blind A/B comparison.

    Python许可证: MIT
    • agent-skills
    • ai-tools
    • claude-code
    • claude-code-plugin
    • claude-code-skill

    github实测增长打开来源 ↗

    安装 /plugin marketplace add shinpr/rashomon

    18GitHub 星标稳定
  9. 9

    技能
    休眠

    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.

    Python
    • ai-agents
    • claude-code-plugin
    • code-review
    • evals
    • python

    github实测增长打开来源 ↗

    安装 /plugin marketplace add prime-radiant-inc/parallel-adversarial-review

    17GitHub 星标稳定
  10. 10

    MCP
    休眠

    MCP as a Judge: a behavioral MCP that strengthens AI coding assistants via explicit LLM evaluations

    Python许可证: MIT

      mcp实测增长打开来源 ↗

      安装 claude mcp add mcp-as-a-judge -- uvx mcp-as-a-judge

      17GitHub 星标稳定
    • 11

      技能
      活跃

      Make Claude write clearly, for everyone.

      Python许可证: 0BSD
      • claude-code
      • claude-code-plugin
      • controlled-language
      • llm-evaluation
      • output-style

      github实测增长打开来源 ↗

      安装 /plugin marketplace add stefanobaghino/simple-output-styles

      16GitHub 星标稳定
    • 12

      其他
      活跃

      A command-line tool to scaffold and manage enterprise-ready AI Agents powered by the A2A (Agent-to-Agent) protocol

      Go许可证: Apache-2.0
      • a2a
      • agents
      • ai
      • containerized
      • docker

      github实测增长打开来源 ↗

      14GitHub 星标+1 (+7.7 %)
    • 13

      MCP
      活跃

      Query Spanlens LLM observability from Cursor, Claude Desktop, or Continue via MCP.

      ↓ 32 下载/周TypeScript许可证: MIT

        mcp实测增长打开来源 ↗

        安装 claude mcp add mcp-server -- npx @spanlens/mcp-server

        13GitHub 星标+1 (+8.3 %)
      • 14

        技能
        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).

        Python许可证: MIT
        • adr
        • agentic-engineering
        • ai-agents
        • anthropic
        • claude-code

        github实测增长打开来源 ↗

        安装 /plugin marketplace add GiustoPiedimonte/agentic-engineering-marketplace

        13GitHub 星标稳定
      • 15

        其他
        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.

        HTML
        • agent-evaluation
        • anthropic
        • claude-code
        • claude-code-skill
        • evals

        github实测增长打开来源 ↗

        13GitHub 星标稳定
      • 16

        技能
        活跃

        Audit which Claude Code skills you actually use — surface dead installs and hallucinated invocations from your session logs.

        TypeScript许可证: MIT
        • anthropic
        • audit
        • claude
        • claude-code
        • claude-code-plugin

        github实测增长打开来源 ↗

        安装 /plugin marketplace add sfrangulov/skill-graveyard

        10GitHub 星标稳定
      • 17

        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
      • 18

        技能
        活跃

        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.

        JavaScript许可证: MIT
        • ai-agents
        • anthropic
        • claude-code
        • claude-code-plugin
        • claude-skill

        github实测增长打开来源 ↗

        安装 /plugin marketplace add CoriChui/bakeoff

        10GitHub 星标稳定
      • 19

        技能
        活跃

        Production-grade AI coding rules for Cursor and Claude Code. 15 rules + 9 doc templates + skills + agents + MCP setup. Drop into any project.

        Python许可证: MIT
        • ai-agents
        • ai-coding
        • ai-development
        • ai-engineer
        • automation

        github实测增长打开来源 ↗

        安装 git clone https://github.com/aiagentwithdhruv/ai-dev-stack ~/.claude/skills/ai-dev-stack

        10GitHub 星标稳定
      • 20

        技能
        休眠

        Local open-source dev tool to debug, secure, and evaluate LLM agents. Provides static analysis, dynamic security checks, and runtime monitoring - integrates with Cursor and Claude Code.

        Python
        • agent-debugging
        • agent-security
        • agent-trace
        • ai-security-tool
        • behavior-analysis

        github实测增长打开来源 ↗

        安装 /plugin marketplace add cylestio/agent-inspector

        9GitHub 星标稳定
      • 21

        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
      • 22

        技能
        休眠

        A self-improving harness router for Claude Code.

        Python许可证: MIT
        • a-b-testing
        • ai-agent
        • ai-orchestration
        • ai-routing
        • ai-workflow

        github实测增长打开来源 ↗

        安装 /plugin marketplace add SeongwoongCho/adaptive-harness

        8GitHub 星标稳定

      学习与参考资源

      Ranked by known GitHub stars, highest first; archived repositories come after maintained repositories. 这些资源可单独访问，不参与主要排名。

      1. 1

        awesome-llm-observability

        技能
        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.

        Python
        • ai-agents
        • ai-engineering
        • ai-observability
        • awesome
        • awesome-list
        github

        安装 git clone https://github.com/ContextJet-ai/awesome-llm-observability ~/.claude/skills/awesome-llm-observability

        资源实测增长
        33GitHub 星标+2 (+6.5 %)
      2. 2

        Agentic_AI_Engineer

        智能体
        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.

        Jupyter Notebook许可证: MIT
        • a2a-protocol
        • agent-orchestration
        • ai-guardrails
        • fastapi
        • kubernetes
        github资源实测增长
        18GitHub 星标稳定
      3. 3

        trigger_tree

        技能
        活跃打开来源 ↗

        Documentation-discovery telemetry for Claude Code — heat/cold maps, health grade, evidence-backed router fixes. 100% local, zero tokens. /tt

        Python许可证: MIT
        • ai-agents
        • claude-code
        • claude-code-plugin
        • docs-as-code
        • documentation
        github

        安装 /plugin marketplace add Hedde/trigger_tree

        资源实测增长
        14GitHub 星标稳定