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

122

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
    休眠

    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.

    Python
    • agent-skills
    • ai-safety
    • anti-lie
    • audit
    • factuality

    github实测增长打开来源 ↗

    安装 git clone https://github.com/lc198707/anti-lie ~/.claude/skills/anti-lie

    89GitHub 星标稳定
  2. 2

    技能
    活跃

    Production patterns for agent orchestrators, harnesses, evals, MCP/A2A interoperability, memory, provider routing, and LLM usage metering.

    Python许可证: MIT
    • a2a
    • agent-orchestration
    • agent-skills
    • ai-agents
    • developer-tools

    github实测增长打开来源 ↗

    安装 git clone https://github.com/ssheleg/agent-stack ~/.claude/skills/agent-stack

    2GitHub 星标+1 (+100.0 %)
  3. 3

    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 星标稳定
  4. 4

    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 %)
  5. 5

    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+2 (+10.0 %)
  6. 6

    技能
    活跃

    Deletion-first Agent Skill for removing test bloat, verification theater, and speculative fallbacks while preserving behavior.

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

    github实测增长打开来源 ↗

    安装 git clone https://github.com/MrZoyo/deslop-GPT ~/.claude/skills/deslop-GPT

    87GitHub 星标+59 (+210.7 %)
  7. 7

    智能体
    休眠

    Real-time debugging proxy for Agent2Agent (A2A) multi-agent systems

    许可证: MIT
    • a2a
    • agent2agent
    • debugging
    • debugging-tool
    • developer-tools

    github实测增长打开来源 ↗

    3GitHub 星标稳定
  8. 8

    智能体
    休眠

    Contract-based testing for LLM agents: hybrid evaluation, multi-agent + A2A, deterministic replay.

    Python许可证: MIT
    • a2a
    • agents
    • contracts
    • evaluation
    • llm

    github实测增长打开来源 ↗

    0GitHub 星标稳定
  9. 9

    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
  10. 10

    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
  11. 11

    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 %)
    • 12

      技能
      活跃

      Axiom is a curated marketplace of shared plugins for Claude Code and Codex.

      Python许可证: MIT
      • agent-skills
      • anthropic
      • claude
      • claude-code
      • claude-code-marketplace

      github实测增长打开来源 ↗

      安装 git clone https://github.com/netopsengineer/axiom ~/.claude/skills/axiom

      5GitHub 星标稳定
    • 13

      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
    • 14

      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+15 (+0.86 %)
    • 15

      智能体
      活跃

      面向长程研发任务的 Java Agent Harness，支持 A2A 跨语言协作、可恢复执行、上下文工程与 Eval 驱动开发。

      Java许可证: Apache-2.0
      • a2a
      • agentic-ai
      • ai-agents
      • developer-tools
      • evals

      github实测增长打开来源 ↗

      0GitHub 星标稳定
    • 16

      智能体
      休眠

      A safety-first multi-agent mental health companion with real-time distress tracking, triple-layer guardrails, and evidence-based grounding techniques. Built for Kaggle × Google Agents Intensive 2025 Capstone (Agents for Good Track)

      Python
      • a2a-protocol
      • agent-evaluation
      • agents-for-good
      • ai-agents
      • crisis-support

      github实测增长打开来源 ↗

      1GitHub 星标稳定
    • 17

      技能
      活跃

      OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

      Python许可证: Apache-2.0
      • agent
      • agent-skills
      • ai-agent
      • alignment
      • evaluation

      github实测增长打开来源 ↗

      安装 git clone https://github.com/agentscope-ai/OpenJudge ~/.claude/skills/OpenJudge

      816GitHub 星标+11 (+1.4 %)
    • 18

      其他
      休眠

      Official Python SDK for GT8004 — AI agent observability with MCP, A2A, x402 payment tracking. FastAPI, Flask, FastMCP middleware included.

      Python许可证: MIT
      • a2a
      • ai-agent
      • analytics
      • fastapi
      • flask

      github实测增长打开来源 ↗

      1GitHub 星标稳定
    • 19

      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
    • 20

      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 %)
    • 21

      MCP
      活跃

      8 MCP SMB products — standalone AI servers for SMBs: Guardrails, FinOps, Observability, Router, Trust Score, Memory, ThinkSecure, A2A Lite. 37 tools, TNC credits billing.

      Python许可证: MIT
      • a2a-protocol
      • ai-governance
      • finops
      • guardrails
      • mcp

      github实测增长打开来源 ↗

      1GitHub 星标稳定
    • 22

      智能体
      休眠

      AgentOps: Multi-agent infrastructure remediation platform. A2A protocol, agent coordination, HITL approval, auto-rollback.

      Python许可证: MIT
      • a2a-protocol
      • ai
      • automation
      • infrastructure
      • llm

      github实测增长打开来源 ↗

      0GitHub 星标稳定
    • 23

      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 ↗

      339GitHub 星标+81 (+31.4 %)
    • 24

      技能
      活跃

      Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters

      Python许可证: MIT
      • agent-skills
      • evals
      • python
      • skills

      github实测增长打开来源 ↗

      安装 git clone https://github.com/adewale/skill-eval-harness ~/.claude/skills/skill-eval-harness

      73GitHub 星标+2 (+2.8 %)
    • 25

      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