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

73

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

    其他
    活跃

    SigNoz is an open-source, OpenTelemetry-native observability platform for your team and their AI agents. Get logs, metrics, and traces in one tool with features like APM, distributed tracing, log management, infra monitoring, etc. Combined…

    github实测增长打开来源 ↗

    32 003GitHub 星标+50 (+0.16 %)
  2. 2

    其他
    活跃

    AI SRE AgenticOps for Kubernetes and cloud infrastructure.

    github实测增长打开来源 ↗

    782GitHub 星标+1 (+0.13 %)
  3. 3

    其他
    活跃

    eBPF-based Networking, Security, and Observability

    github实测增长打开来源 ↗

    25 047GitHub 星标+29 (+0.12 %)
  4. 4

    其他
    活跃

    The fastest path to AI-powered full stack observability, even for lean teams.

    github实测增长打开来源 ↗

    80 412GitHub 星标+85 (+0.11 %)
  5. 5

    智能体
    活跃

    eBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.

    github实测增长打开来源 ↗

    12 068GitHub 星标+8 (+0.07 %)
  6. 6
    活跃

    A 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
  7. 7

    其他
    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
  8. 8
    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-platform

    198GitHub 星标-1 (-0.50 %)
  9. 9

    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.

    github实测增长打开来源 ↗

    254GitHub 星标-3 (-1.2 %)
  10. 10
    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 %)
  11. 11
    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-bench

    51GitHub 星标-5 (-8.9 %)
  12. 12
    活跃

    Production reliability, benchmarking, and evaluation layer for MCP agent runtimes — protocol negotiation, A2A interop, circuit breakers, connection pooling, adaptive streaming, and autoscaling, with measured throughput/latency and a…

    github实测增长打开来源 ↗

    3GitHub 星标稳定
  13. 13
    活跃

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

    github实测增长打开来源 ↗

    0GitHub 星标稳定
  14. 14

    智能体
    活跃

    Generic DeepSeek Harness (dsh) plugins: A2A protocol server, session storage mirror, and Langfuse observability.

    github实测增长打开来源 ↗

    1GitHub 星标稳定
  15. 15

    MCP
    活跃

    A typed, replayable, budget-aware programming language for LLM agents. Compiles to Python & TypeScript.

    github实测增长打开来源 ↗

    2GitHub 星标稳定
  16. 16

    技能
    活跃

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

    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 %)
  17. 17
    活跃

    Multi-agent quality gate skill for Claude Code that researches, reviews, tests and challenges AI-generated work before the final answer.

    github实测增长打开来源 ↗

    安装 git clone https://github.com/ma-nucho-pro/supervisor-skill-claude ~/.claude/skills/supervisor-skill-claude

    2GitHub 星标稳定
  18. 18

    智能体
    活跃

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

    github实测增长打开来源 ↗

    1GitHub 星标稳定
  19. 19
    活跃

    Local-first Agentic AI Infrastructure Platform with LLM Gateway, Agent DAG Runtime, MCP Tool Hub, A2A Agent Mesh, Local RAG, Tool Sandbox and Observability.

    github实测增长打开来源 ↗

    1GitHub 星标稳定
  20. 20

    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。

    github实测增长打开来源 ↗

    0GitHub 星标稳定
  21. 21

    智能体
    活跃

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

    github实测增长打开来源 ↗

    0GitHub 星标稳定
  22. 22

    MCP
    活跃

    Open-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 %)
  23. 23

    技能
    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/claudestat

    34GitHub 星标+1 (+3.0 %)
  24. 24
    活跃

    AgentGateway — independent third-party profile of a public API surface, by API Evangelist. AgentGateway is an open-source, AI-native proxy and gateway for routing, observing, and governing traffic to and from AI agents, LLM providers, and…

    github实测增长打开来源 ↗

    0GitHub 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. 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