Die Werkzeugbeschreibungen sind auf Englisch.

LLM-Beobachtbarkeit

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

Anwendungsfall

Aktivität

Sortieren nach

115

Werkzeug-Rangliste

Ranked by normalized popularity across sources. Rohwerte behalten ihr eigenes Zeitfenster; eine Änderung erfordert mindestens zwei Messungen in 7 Tagen.

  1. 1

    Skill
    Aktiv

    🪢 Langfuse documentation -- Langfuse is the open source LLM Engineering Platform. Observability, evals, prompt management, playground and metrics to debug and improve LLM apps

    MDXLizenz: MIT
    • agent-skills
    • agents
    • genai
    • hacktoberfest
    • langfuse

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/langfuse/langfuse-docs ~/.claude/skills/langfuse-docs

    239GitHub-Sterne+3 (+1.3 %)
  2. 2

    Skill
    Aktiv

    🟪 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.

    PythonLizenz: GPL-3.0
    • a2a-protocol
    • ag-ui-protocol
    • agent-platform
    • agentic-ai
    • agents

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/Idun-Group/idun-agent-platform ~/.claude/skills/idun-agent-platform

    198GitHub-Sterne-1 (-0.50 %)
  3. 3

    Agent
    Aktiv

    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…

    PythonLizenz: Apache-2.0
    • a2a
    • adk
    • ai-agents
    • aws
    • azure

    githubgemessenes WachstumQuelle öffnen ↗

    156GitHub-Sterne+19 (+13.9 %)
  4. 4

    Skill
    Aktiv

    Research-backed, eval-driven skills for AI agents

    PythonLizenz: Apache-2.0
    • agent-skills
    • ai-agents
    • codex
    • design
    • evals

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/ZSeven-W/craft-skills ~/.claude/skills/craft-skills

    142GitHub-Sterne+18 (+14.5 %)
  5. 5

    Sonstige
    Aktiv

    Evidence-first infrastructure for reproducible, isolated executable evaluation and online rewards.

    PythonLizenz: Apache-2.0
    • benchmark
    • kubernetes
    • llm-evaluation
    • llm-infrastructure
    • ray

    githubgemessenes WachstumQuelle öffnen ↗

    140GitHub-Sterne+24 (+20.7 %)
  6. 6

    Skill
    Aktiv

    🐙 ADLC Team Skills — Agentic SDLC for Engineering Teams

    ShellLizenz: MIT
    • adr
    • agent-skills
    • agentic-sdlc
    • ai-coding
    • developer-tools

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/tikalk/adlc-team-skills ~/.claude/skills/adlc-team-skills

    132GitHub-Sterne+1 (+0.76 %)
  7. 7

    Skill
    Aktiv

    Skills, prompts, and instructions for building AI agents on top of Dynatrace production context

    JavaScriptLizenz: Apache-2.0
    • agent-skills
    • ai-agents
    • claude-code
    • devops
    • dql

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/Dynatrace/dynatrace-for-ai ~/.claude/skills/dynatrace-for-ai

    132GitHub-Sterne+4 (+3.1 %)
  8. 8

    Sonstige
    Aktiv

    Self-hosted AI SRE for Kubernetes — zero-instrumentation eBPF observability plus a copilot that fixes issues through guardrailed, self-verifying actions. BYO-LLM, air-gapped capable.

    GoLizenz: Apache-2.0
    • ai-agent
    • aiops
    • clickhouse
    • devops
    • ebpf

    githubgemessenes WachstumQuelle öffnen ↗

    131GitHub-Sterne-4 (-3.0 %)
  9. 9

    MCP
    Aktiv

    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…

    JavaScriptLizenz: MIT
    • agent-orchestration
    • agent-skill
    • agent-skills
    • ai-agents
    • ai-coding

    githubgemessenes WachstumQuelle öffnen ↗

    129GitHub-Sterne-4 (-3.0 %)
  10. 10

    MCP
    Aktiv

    A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability

    PythonLizenz: MIT
    • agent-skills
    • ai-agents
    • claude-code
    • codex
    • developer-tools

    githubgemessenes WachstumQuelle öffnen ↗

    105GitHub-Sternestabil
  11. 11

    MCP
    Aktiv

    Self improving agents through iterations

    PythonLizenz: Apache-2.0
    • agent-learning
    • agent-memory
    • agentic-workflows
    • ai-agents
    • claude-code

    githubgemessenes WachstumQuelle öffnen ↗

    105GitHub-Sterne+1 (+0.96 %)
  12. 12

    Skill
    Aktiv

    Vendor-neutral OpenTelemetry skills for AI coding agents, grounded in upstream sources

    ShellLizenz: Apache-2.0
    • agent-skills
    • ai
    • observability
    • opentelemetry

    githubgemessenes WachstumQuelle öffnen ↗

    Installieren git clone https://github.com/ollygarden/opentelemetry-agent-skills ~/.claude/skills/opentelemetry-agent-skills

    97GitHub-Sterne+4 (+4.3 %)
  13. 13

    Skill
    Ruhend

    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

    githubgemessenes WachstumQuelle öffnen ↗

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

    89GitHub-Sternestabil
  14. 14

    MCP
    Aktiv

    MCP server for Langfuse LLM observability — trace and observation analysis.

    TypeScriptLizenz: MIT

      mcpgemessenes WachstumQuelle öffnen ↗

      Installieren claude mcp add langfuse -- npx langfuse-observability-mcp-server

      78GitHub-Sternestabil
    • 15

      Skill
      Aktiv

      local-first analytics for AI agent skills

      TypeScript
      • agent-skills
      • analytics
      • bun
      • claude-code
      • cli

      githubgemessenes WachstumQuelle öffnen ↗

      Installieren git clone https://github.com/crafter-station/skill-kit ~/.claude/skills/skill-kit

      77GitHub-Sterne+1 (+1.3 %)
    • 16

      Skill
      Aktiv

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

      PythonLizenz: MIT
      • agent-skills
      • evals
      • python
      • skills

      githubgemessenes WachstumQuelle öffnen ↗

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

      73GitHub-Sterne+4 (+5.8 %)
    • 17

      Sonstige
      Aktiv

      AgentX python SDK. Build multi-agent AI workforce. Run evaluation. Trace your agent. Full Observability.

      PythonLizenz: Apache-2.0
      • a2a
      • agent
      • agent-monitoring
      • evaluation
      • mcp

      githubgemessenes WachstumQuelle öffnen ↗

      68GitHub-Sternestabil
    • 18

      Skill
      Aktiv

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

      PythonLizenz: MIT
      • agent-skills
      • claude
      • claude-ai
      • claude-code
      • claude-skills

      githubgemessenes WachstumQuelle öffnen ↗

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

      55GitHub-Sterne+27 (+96.4 %)
    • 19

      Skill
      Aktiv

      Open benchmark for Claude Code SEO skills — real headless execution against fixture sites with planted-defect answer keys. Deterministic scoring, pre-registered rubric.

      JavaScriptLizenz: MIT
      • aeo
      • agent-skills
      • ai
      • ai-seo
      • benchmark

      githubgemessenes WachstumQuelle öffnen ↗

      Installieren git clone https://github.com/aleclindz/seo-skill-bench ~/.claude/skills/seo-skill-bench

      51GitHub-Sterne-5 (-8.9 %)
    • 20

      MCP
      Aktiv

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

      TypeScriptLizenz: Apache-2.0
      • agent-management
      • agent-ops
      • agent-orchestration
      • ai-agent-platform
      • ai-agents

      githubgemessenes WachstumQuelle öffnen ↗

      50GitHub-Sterne+2 (+4.2 %)
    • 21

      Skill
      Aktiv

      Agent skills for Arize — datasets, experiments, and traces via the ax CLI

      PythonLizenz: MIT
      • agent-skills
      • ai-agents
      • ai-observability
      • arize
      • claude-code

      githubgemessenes WachstumQuelle öffnen ↗

      Installieren git clone https://github.com/Arize-ai/arize-skills ~/.claude/skills/arize-skills

      47GitHub-Sternestabil
    • 22

      MCP
      Aktiv

      Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

      PythonLizenz: Apache-2.0
      • agent-optimization
      • agent-skills
      • agentic-ai
      • ai-agents
      • claude

      githubgemessenes WachstumQuelle öffnen ↗

      47GitHub-Sterne+1 (+2.2 %)
    • 23

      Skill
      Aktiv

      Mini Program Engineering Skill Suite is an Agent Skill suite for evidence‑first mini‑program development. It helps agents bring WeChat or other mini‑program projects from vague intent to reliable engineering work: project intake, product…

      PythonLizenz: MIT
      • agent-skills
      • ai-agents
      • alipay
      • ci-cd
      • claude-code

      githubgeschätztes MomentumQuelle öffnen ↗

      Installieren git clone https://github.com/NocodeMrLi/mini-program-engineering-skill-suite ~/.claude/skills/mini-program-engineering-skill-suite

      39GitHub-Sterne—
    • 24

      Skill
      Aktiv

      Real-time execution trace and cost intelligence for Claude Code

      TypeScriptLizenz: MIT
      • agentic-workflow
      • ai-productivity
      • anthropic
      • anthropic-claude
      • claude

      githubgemessenes WachstumQuelle öffnen ↗

      Installieren /plugin marketplace add DeibyGS/claudestat

      34GitHub-Sterne+1 (+3.0 %)

    Lern- und Referenzressourcen

    Ranked by normalized popularity across sources. Diese Ressourcen bleiben getrennt zugänglich und fließen nicht in die Hauptwertung ein.

    1. 1

      awesome-agentic-devops

      MCP
      AktivQuelle öffnen ↗

      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.

      PythonLizenz: MIT
      • agent-skills
      • agentic-ai
      • agentic-devops
      • ai-agents
      • awesome
      githubRessourcegemessenes Wachstum
      77GitHub-Sternestabil