Die Werkzeugbeschreibungen sind auf Englisch.

LLM-Beobachtbarkeit

Monitoring, Traces, Bewertung und Qualität von LLM-Anwendungen.

Anwendungsfall

Aktivität

Sortieren nach

115

Werkzeug-Rangliste

Nach gemessenem Wachstum und quellenübergreifend normalisiert sortiert. Rohwerte behalten ihr eigenes Zeitfenster; eine Änderung erfordert mindestens zwei Messungen in 7 Tagen.

  1. 1
    Aktiv

    Claude Code skills where every entry ships receipts — accuracy-gated benchmarks against baseline and placebo, rejects published

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/sjh9714/skill-receipts ~/.claude/skills/skill-receipts

    2GitHub-Sternestabil
  2. 2

    Skill
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

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

    2GitHub-Sterne+1 (+100.0 %)
  3. 3

    Agent
    Aktiv

    A lightweight Python library that decouples agentic runtime from applications it builds

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sternestabil
  4. 4
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

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

    2GitHub-Sternestabil
  5. 5

    Sonstige
    Ruhend

    Multi-agent customer support system with Google ADK & Gemini 2.5 Flash Lite. Kaggle capstone demonstrating 11+ concepts. Automates 80%+ queries, <10s response time.

    githubgemessenes WachstumQuelle öffnen ↗

    2GitHub-Sternestabil
  6. 6

    Agent
    Ruhend

    A Multi-Agent System (MAS) evaluation framework using PydanticAI that generates and evaluates scientific paper reviews through a three-tiered assessment approach: traditional metrics, LLM-as-a-Judge, and graph-based complexity analysis.

    githubgemessenes WachstumQuelle öffnen ↗

    2GitHub-Sternestabil
  7. 7
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sternestabil
  8. 8
    Aktiv

    Agent 降智检测与自愈公评网络 — an immune system for the AI agent society

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sternestabil
  9. 9

    Sonstige
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sternestabil
  10. 10

    Agent
    Ruhend

    The reliability and interoperability layer for AI agents. A2A-native. MCP-bridged.

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sternestabil
  11. 11

    Agent
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sterne+1
  12. 12
    Aktiv

    Skill instalable para Claude Code que mide si tu agente cumple las reglas establecidas. Lee el historial de sesiones de tu disco y devuelve un porcentaje por regla de cumplimiento. Sin instalar nada, sin red, biblioteca estándar.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add jleonceo/skill-adherencia-reglas

    1GitHub-Sternestabil
  13. 13
    Aktiv

    Mide si tu agente de IA cumple las reglas que le escribiste. Lee el historial local de Claude Code y devuelve un porcentaje por regla. Sin instalar nada, sin red, biblioteca estándar.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/jleonceo/adherencia-reglas ~/.claude/skills/adherencia-reglas

    1GitHub-Sternestabil
  14. 14

    Agent
    Ruhend

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

    githubgemessenes WachstumQuelle öffnen ↗

    0GitHub-Sternestabil
  15. 15
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sternestabil
  16. 16

    Agent
    Aktiv

    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。

    githubgemessenes WachstumQuelle öffnen ↗

    0GitHub-Sternestabil
  17. 17

    Agent
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    0GitHub-Sternestabil
  18. 18

    Agent
    Aktiv

    A2A green-agent orchestrator for evaluating agents on the AppWorld benchmark, built on the AgentBeats SDK

    githubgemessenes WachstumQuelle öffnen ↗

    0GitHub-Sternestabil
  19. 19

    Sonstige
    Aktiv

    🔑 HomeStream · 家园·流 — 零成本自托管多Agent协作框架,通往AI世界的那把钥匙 | Zero-cost self-hosted multi-agent framework — The key to AI world

    githubgemessenes WachstumQuelle öffnen ↗

    0GitHub-Sternestabil
  20. 20
    Ruhend

    A Python proof-of-concept for tracing multi-turn Agent-to-Agent (A2A) conversations as a single unified MLflow trace for LLM observability and evaluation.

    githubgemessenes WachstumQuelle öffnen ↗

    0GitHub-Sternestabil
  21. 21

    MCP
    Aktiv

    Open-source, self-hosted control plane for OpenClaw and Hermes AI-agent fleets on Docker/Kubernetes — REST, CLI, and MCP.

    githubgemessenes WachstumQuelle öffnen ↗

    50GitHub-Sterne+2 (+4.2 %)
  22. 22

    Skill
    Aktiv

    Real-time execution trace and cost intelligence for Claude Code

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add DeibyGS/claudestat

    34GitHub-Sterne+1 (+3.0 %)
  23. 23
    Aktiv

    Make Claude Opus 4.8 behave like Claude Fable 5 — doctrine output style, drift-catching hooks, and an eval loop against golden Fable transcripts. Claude Code plugin.

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren /plugin marketplace add rennf93/opus-fable-playbook

    33GitHub-Sternestabil
  24. 24
    Aktiv

    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…

    githubgemessenes WachstumQuelle öffnen ↗

    0GitHub-Sternestabil
  25. 25
    Ruhend

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

    githubgemessenes WachstumQuelle öffnen ↗

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

    27GitHub-Sternestabil