Die Werkzeugbeschreibungen sind auf Englisch.

LLM-Beobachtbarkeit

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

Anwendungsfall

Aktivität

Sortieren nach

123

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

    MCP
    Aktiv

    Query Spanlens LLM observability from Cursor, Claude Desktop, or Continue via MCP.

    ↓ 32 Downloads/WocheTypeScriptLizenz: MIT

      mcpgemessenes WachstumQuelle öffnen ↗

      Installieren claude mcp add mcp-server -- npx @spanlens/mcp-server

      12GitHub-Sternestabil
    • 2

      MCP
      Aktiv

      CLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.

      PythonLizenz: MIT
      • agent-benchmark
      • agent-evaluation
      • ai-coding-agents
      • ai-evaluation
      • claude-code

      githubgemessenes WachstumQuelle öffnen ↗

      12GitHub-Sternestabil
    • 3

      Skill
      Aktiv

      Turn one decision into a judged tournament of solutions, then pick the best — a Claude Code skill that generates candidates, auto-derives the rubric, judges independently, and returns a defensible winner.

      JavaScriptLizenz: MIT
      • ai-agents
      • anthropic
      • claude-code
      • claude-code-plugin
      • claude-skill

      githubgemessenes WachstumQuelle öffnen ↗

      Installieren /plugin marketplace add CoriChui/bakeoff

      10GitHub-Sternestabil
    • 4

      Sonstige
      Aktiv

      A Go-native framework for LLM agents, with OpenTelemetry observability built in.

      GoLizenz: Apache-2.0
      • a2a
      • agents
      • ai
      • anthropic
      • bedrock

      githubgemessenes WachstumQuelle öffnen ↗

      10GitHub-Sternestabil
    • 5

      Skill
      Ruhend

      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

      githubgemessenes WachstumQuelle öffnen ↗

      Installieren /plugin marketplace add cylestio/agent-inspector

      9GitHub-Sternestabil
    • 6

      Skill
      Aktiv

      Anchor — the production-grade AGENTS.md template for AI coding agents. 51 sections of battle-tested rules. Keep your agents grounded.

      Lizenz: MIT
      • agent-instructions
      • agents-md
      • ai-agent-instructions
      • ai-coding
      • ai-coding-agent

      githubgemessenes WachstumQuelle öffnen ↗

      Installieren git clone https://github.com/peva3/anchor ~/.claude/skills/anchor

      8GitHub-Sternestabil
    • 7

      Skill
      Ruhend

      A self-improving harness router for Claude Code.

      PythonLizenz: MIT
      • a-b-testing
      • ai-agent
      • ai-orchestration
      • ai-routing
      • ai-workflow

      githubgemessenes WachstumQuelle öffnen ↗

      Installieren /plugin marketplace add SeongwoongCho/adaptive-harness

      8GitHub-Sternestabil
    • 8

      Agent
      Aktiv

      MemroOS / memroos: memory OS and governance layer for AI agents, agent workflows, dispatch, proof, and context continuity.

      TypeScript
      • a2a
      • agent-governance
      • agent-memory
      • agent-orchestration
      • agent-workflows

      githubgemessenes WachstumQuelle öffnen ↗

      7GitHub-Sternestabil
    • 9

      Skill
      Aktiv

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

      PythonLizenz: MIT
      • agent-skills
      • anthropic
      • claude
      • claude-code
      • claude-code-marketplace

      githubgemessenes WachstumQuelle öffnen ↗

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

      5GitHub-Sternestabil
    • 10

      Skill
      Ruhend

      An assembly line for AI software development. 35 skills, 11 agent personas, 29 commands. From raw idea to shipped code.

      ShellLizenz: MIT
      • agentic-engineering
      • agents
      • claude-code
      • claude-code-plugin
      • claude-code-skills

      githubgemessenes WachstumQuelle öffnen ↗

      Installieren /plugin marketplace add aneja5/forge-skills

      3GitHub-Sternestabil
    • 11

      Agent
      Aktiv

      Multi-agent SRE on-call investigator that auto-triages Slack/Discord infrastructure alerts via AWS Bedrock AgentCore, fanning out to specialized agents (CloudWatch, EKS, Slack/Discord scanners) for parallel investigation.

      Python
      • a2a-protocol
      • anthropic
      • aws-bedrock
      • aws-lambda
      • bedrock-agentcore

      githubgemessenes WachstumQuelle öffnen ↗

      3GitHub-Sternestabil
    • 12

      MCP
      Aktiv

      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…

      PythonLizenz: Apache-2.0
      • a2a-protocol
      • agent-to-agent
      • ai-agents
      • async-python
      • autoscaling

      githubgemessenes WachstumQuelle öffnen ↗

      3GitHub-Sternestabil
    • 13

      Agent
      Ruhend

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

      Lizenz: MIT
      • a2a
      • agent2agent
      • debugging
      • debugging-tool
      • developer-tools

      githubgemessenes WachstumQuelle öffnen ↗

      3GitHub-Sternestabil
    • 14

      Sonstige
      Aktiv

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

      PythonLizenz: MIT
      • a2a-protocol
      • agent-evaluation
      • google-adk
      • multi-agent-system
      • observability

      githubgemessenes WachstumQuelle öffnen ↗

      2GitHub-Sternestabil
    • 15

      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.

      PythonLizenz: Apache-2.0
      • a2a-protocol
      • agent-evaluation
      • agentbeats
      • ai-agents
      • benchmarks

      githubgemessenes WachstumQuelle öffnen ↗

      2GitHub-Sternestabil
    • 16

      Skill
      Aktiv

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

      JavaScriptLizenz: MIT
      • agent-skills
      • ai-agents
      • anthropic
      • benchmark
      • claude

      githubgemessenes WachstumQuelle öffnen ↗

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

      2GitHub-Sternestabil
    • 17

      Skill
      Aktiv

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

      • agentic-coding
      • agentic-workflow
      • ai-agent-skills
      • ai-code-review
      • ai-workflows

      githubgemessenes WachstumQuelle öffnen ↗

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

      2GitHub-Sternestabil
    • 18

      Skill
      Aktiv

      Glanceable Claude Code and Codex state in your terminal tabs: white=idle, blue=working, orange=waiting. Multi-terminal (iTerm2, WezTerm, AI Power Term), a live status bar with Anthropic usage limits, /sfl and /nil window save-and-restore,…

      ShellLizenz: MIT
      • ai-workflow-observability
      • claude-code
      • claude-code-hooks
      • claude-code-skill
      • claude-code-skills

      githubgemessenes WachstumQuelle öffnen ↗

      Installieren git clone https://github.com/wasulajr/headsup ~/.claude/skills/headsup

      1GitHub-Sternestabil
    • 19

      Sonstige
      Aktiv

      Terminal-first validation harness for reviewing PRDs, RFCs, strategy docs, and experiment plans.

      TypeScript
      • ai-agents
      • claude-code
      • claude-code-skills
      • cli
      • evals

      githubgemessenes WachstumQuelle öffnen ↗

      1GitHub-Sternestabil
    • 20

      Skill
      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.

      PythonLizenz: MIT
      • ai-evaluation
      • claude
      • claude-code
      • claude-code-plugin
      • claude-code-skill

      githubgemessenes WachstumQuelle öffnen ↗

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

      1GitHub-Sternestabil
    • 21

      Agent
      Ruhend

      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

      githubgemessenes WachstumQuelle öffnen ↗

      1GitHub-Sternestabil
    • 22

      Sonstige
      Ruhend

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

      PythonLizenz: MIT
      • a2a
      • ai-agent
      • analytics
      • fastapi
      • flask

      githubgemessenes WachstumQuelle öffnen ↗

      1GitHub-Sternestabil
    • 23

      Agent
      Aktiv

      The agent framework where the model never holds the trigger — every consequential action clears your policy first, waits for a human when it matters, and lands on a record you can verify. Build on it, or put it around the agent you already…

      PythonLizenz: Apache-2.0
      • a2a
      • agent-framework
      • ai-agents
      • ai-governance
      • ai-safety

      githubgemessenes WachstumQuelle öffnen ↗

      1GitHub-Sternestabil
    • 24

      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.

      Python
      • a2a
      • agent-runtime
      • ai-infra
      • deepseek
      • fastapi

      githubgemessenes WachstumQuelle öffnen ↗

      1GitHub-Sternestabil

    Lern- und Referenzressourcen

    Nach gemessenem Wachstum und quellenübergreifend normalisiert sortiert. Diese Ressourcen bleiben getrennt zugänglich und fließen nicht in die Hauptwertung ein.

    1. 1

      tunelab

      Skill
      AktivQuelle öffnen ↗

      Claude Code plugin for LLM fine-tuning, distillation, and evaluation — decide whether you need fine-tuning at all, distill your LLM logs into small local models (MLX/LoRA), evaluate with held-out discipline, and learn the why at every step.

      PythonLizenz: MIT
      • claude-code
      • claude-code-plugin
      • distillation
      • fine-tuning
      • llm-evaluation
      github

      Installieren /plugin marketplace add rchaz/tunelab

      Ressourcegemessenes Wachstum
      6GitHub-Sternestabil