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

112

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

    Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.

    Python许可证: Apache-2.0
    • agent-memory
    • agent-skills
    • ai-agents
    • benchmark
    • dataset

    github实测增长打开来源 ↗

    安装 git clone https://github.com/EverMind-AI/SkillCorpus ~/.claude/skills/SkillCorpus

    360GitHub 星标+168 (+87.5 %)
  2. 2

    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

    363GitHub 星标+58 (+19.0 %)
  3. 3

    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

    138GitHub 星标+21 (+17.9 %)
  4. 4

    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

    38GitHub 星标+10 (+35.7 %)
  5. 5

    其他
    活跃

    Mastra is the modern TypeScript framework for AI-powered applications and agents.

    TypeScript
    • agents
    • ai
    • chatbots
    • evals
    • javascript

    github实测增长打开来源 ↗

    27 601GitHub 星标+128 (+0.47 %)
  6. 6

    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 565GitHub 星标+58 (+2.3 %)
  7. 7

    MCP
    活跃

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

    Shell
    • a2a
    • agent-framework
    • agentic-ai
    • ai
    • ai-agents

    github实测增长打开来源 ↗

    2GitHub 星标+1 (+100.0 %)
  8. 8

    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 %)
  9. 9

    智能体
    活跃

    A local A2A event and continuity service for agent applications, with structured history, provenance-safe transcripts, literal search, and natural-language queries.

    Python许可证: BSD-2-Clause
    • a2a
    • agent-memory
    • ai-agents
    • event-sourcing
    • fastapi

    github实测增长打开来源 ↗

    1GitHub 星标+1
  10. 10

    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 ↗

    146GitHub 星标+13 (+9.8 %)
  11. 11

    智能体
    活跃

    DataBuff is an AI-native APM built on Opentelemetry，with multi-agent troubleshooting out of the box.

    Java许可证: AGPL-3.0
    • aiops
    • apm
    • application-monitoring
    • devops
    • distributed-tracing

    github实测增长打开来源 ↗

    627GitHub 星标+22 (+3.6 %)
  12. 12

    其他
    活跃

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

    Go许可证: GPL-3.0
    • ai
    • alerting
    • cncf
    • data-visualization
    • database

    github实测增长打开来源 ↗

    80 382GitHub 星标+80 (+0.10 %)
  13. 13

    技能
    活跃

    Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.

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

    github实测增长打开来源 ↗

    安装 git clone https://github.com/FrancyJGLisboa/agent-skill-creator ~/.claude/skills/agent-skill-creator

    2 358GitHub 星标+29 (+1.2 %)
  14. 14

    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…

    TypeScript
    • apm
    • application-monitoring
    • distributed-tracing
    • go
    • good-first-issue

    github实测增长打开来源 ↗

    31 983GitHub 星标+48 (+0.15 %)
  15. 15

    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 752GitHub 星标+22 (+1.3 %)
  16. 16

    技能
    活跃

    The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.

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

    github实测增长打开来源 ↗

    安装 git clone https://github.com/Sahir619/fable-method ~/.claude/skills/fable-method

    2 269GitHub 星标+22 (+0.98 %)
  17. 17

    智能体
    活跃

    Amazon Bedrock AgentCore enterprise platform accelerator with AWS CDK, Terraform organization guardrails, MCP/A2A agents, security, memory, and observability.

    Python许可证: Apache-2.0
    • a2a-protocol
    • agentcore
    • agentcore-agent
    • agentcore-gateway
    • agentcore-identity

    github实测增长打开来源 ↗

    5GitHub 星标+1 (+25.0 %)
  18. 18

    MCP
    休眠

    Open-source Python framework to deploy AI agents via HTTP, A2A, and MCP with built-in observability

    Python许可证: MIT
    • a2a
    • a2a-client
    • a2a-server
    • agent-evaluation
    • agentic-ai

    github实测增长打开来源 ↗

    5GitHub 星标+1 (+25.0 %)
  19. 19

    MCP
    活跃

    🫖 Status page with uptime monitoring & API monitoring as code 🫖

    TypeScript许可证: AGPL-3.0
    • alerting
    • incident-management
    • mcp
    • mcp-server
    • monitoring

    github实测增长打开来源 ↗

    9 045GitHub 星标+28 (+0.31 %)
  20. 20

    技能
    活跃

    A test runner for agentskills.io-style AI agent skills

    TypeScript许可证: MIT
    • agent-evals
    • agent-skills
    • agentskills
    • ai-agents
    • cli

    github实测增长打开来源 ↗

    安装 git clone https://github.com/darkrishabh/agent-skills-eval ~/.claude/skills/agent-skills-eval

    713GitHub 星标+12 (+1.7 %)
  21. 21

    其他
    活跃

    eBPF-based Networking, Security, and Observability

    Go许可证: Apache-2.0
    • bpf
    • cncf
    • cni
    • containers
    • ebpf

    github实测增长打开来源 ↗

    25 035GitHub 星标+26 (+0.10 %)
  22. 22

    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 ↗

    19GitHub 星标+2 (+11.8 %)
  23. 23

    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

    72GitHub 星标+4 (+5.9 %)
  24. 24

    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 %)
  25. 25

    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

    131GitHub 星标+5 (+4.0 %)