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.
- 1Aktiv
skill-receipts
SkillClaude 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-receipts2GitHub-Sternestabil - 2Aktiv
agent-stack
SkillProduction 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-stack2GitHub-Sterne+1 (+100.0 %) - 3Aktiv
pyxen
AgentA lightweight Python library that decouples agentic runtime from applications it builds
githubgemessenes WachstumQuelle öffnen ↗
1GitHub-Sternestabil - 4Aktiv
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-claude2GitHub-Sternestabil - 5Ruhend
CustoFlow
SonstigeMulti-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 - 6Ruhend
Agents-eval
AgentA 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 - 7Aktiv
boundary-bench
AgentDeterministic crash tests for agent control planes: paired worlds, hard stops, budgets, scopes, approvals, and hash-linked receipts.
githubgemessenes WachstumQuelle öffnen ↗
1GitHub-Sternestabil - 8Aktiv
DriftSentinel
AgentAgent 降智检测与自愈公评网络 — an immune system for the AI agent society
githubgemessenes WachstumQuelle öffnen ↗
1GitHub-Sternestabil - 9Aktiv
DeepSeek-Infra
SonstigeLocal-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 - 10Ruhend
primal-core
AgentThe reliability and interoperability layer for AI agents. A2A-native. MCP-bridged.
githubgemessenes WachstumQuelle öffnen ↗
1GitHub-Sternestabil - 11Aktiv
historian
AgentA 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 - 12Aktiv
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-reglas1GitHub-Sternestabil - 13Aktiv
adherencia-reglas
SkillMide 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-reglas1GitHub-Sternestabil - 14Ruhend
agentanvil
AgentContract-based testing for LLM agents: hybrid evaluation, multi-agent + A2A, deterministic replay.
githubgemessenes WachstumQuelle öffnen ↗
0GitHub-Sternestabil - 15Aktiv
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 - 16Aktiv
CodeFlow
Agent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 - 17Aktiv
evoagent-os
AgentLocal-first control plane for durable, governed agent teams: DAG orchestration, approvals, memory, signed skills, trace contracts, and realtime.
githubgemessenes WachstumQuelle öffnen ↗
0GitHub-Sternestabil - 18Aktiv
green-agent
AgentA2A green-agent orchestrator for evaluating agents on the AppWorld benchmark, built on the AgentBeats SDK
githubgemessenes WachstumQuelle öffnen ↗
0GitHub-Sternestabil - 19Aktiv
homestream
Sonstige🔑 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 - 20Ruhend
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 - 21Aktiv
nora
MCPOpen-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 %) - 22Aktiv
claudestat
SkillReal-time execution trace and cost intelligence for Claude Code
githubgemessenes WachstumQuelle öffnen ↗
Installieren
/plugin marketplace add DeibyGS/claudestat34GitHub-Sterne+1 (+3.0 %) - 23Aktiv
opus-fable-playbook
SkillMake 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-playbook33GitHub-Sternestabil - 24Aktiv
agentgateway
MCPAgentGateway — 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 - 25Ruhend
🔍 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-skill27GitHub-Sternestabil