Osservabilità LLM

Classifica degli strumenti

Classifica per crescita misurata e normalizzata tra le fonti. I valori grezzi mantengono la propria finestra; una variazione richiede almeno due rilevazioni in 7 giorni.

1. 1

   DeepSeek-Infra

   Altro

   AttivoUltimo commit 4 giorni fa · 2026-09-02

   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

   githubcreato 3 mesi facrescita misurataApri fonte ↗

   1stelle GitHubstabile
2. 2

   DriftSentinel

   Agente

   AttivoUltimo commit 2 mesi fa · 2026-06-20

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

   TypeScriptLicenza: MIT

   • a2a
   • agent
   • agent-guard
   • ai-sre
   • drift-detection

   githubcreato 2 mesi facrescita misurataApri fonte ↗

   1stelle GitHubstabile
3. 3

   skill-eval-harness

   Skill

   AttivoUltimo commit 6 giorni fa · 2026-08-31

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

   PythonLicenza: MIT

   • agent-skills
   • evals
   • python
   • skills

   githubcreato 2 mesi facrescita misurataApri fonte ↗

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

   73stelle GitHub+1 (+1.4 %)
4. 4

   skill-adherencia-reglas

   Skill

   AttivoUltimo commit 36 giorni fa · 2026-07-31

   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.

   PythonLicenza: MIT

   • ai-evaluation
   • claude
   • claude-code
   • claude-code-plugin
   • claude-code-skill

   githubcreato 40 giorni facrescita misurataApri fonte ↗

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

   1stelle GitHubstabile
5. 5

   AgentX-Python

   Altro

   AttivoUltimo commit oggi · 2026-09-06

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

   PythonLicenza: Apache-2.0

   • a2a
   • agent
   • agent-monitoring
   • evaluation
   • mcp

   githubcreato 2 anni facrescita misurataApri fonte ↗

   68stelle GitHubstabile
6. 6

   SkillForge

   Skill

   AttivoUltimo commit 38 giorni fa · 2026-07-29

   A skill creator that proves its skills work. Evidence-driven skill creation for Claude Code and Codex: baseline-tested generation, per-skill regression evals, ecosystem doctor, cross-runtime compile, and an opt-in proactive advisor.

   PythonLicenza: MIT

   • agent-skills
   • claude-ai
   • claude-code
   • claude-skills
   • codex

   githubcreato 8 mesi facrescita misurataApri fonte ↗

   Installa git clone https://github.com/tripleyak/SkillForge ~/.claude/skills/SkillForge

   885stelle GitHub+1 (+0.11 %)
7. 7

   adherencia-reglas

   Skill

   AttivoUltimo commit 36 giorni fa · 2026-07-31

   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.

   PythonLicenza: MIT

   • agent-evaluation
   • ai-agents
   • claude-code
   • claude-code-skill
   • claude-code-skills

   githubcreato 40 giorni facrescita misurataApri fonte ↗

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

   1stelle GitHubstabile
8. 8

   seo-skill-bench

   Skill

   AttivoUltimo commit 15 giorni fa · 2026-08-21

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

   JavaScriptLicenza: MIT

   • aeo
   • agent-skills
   • ai
   • ai-seo
   • benchmark

   githubcreato 2 mesi facrescita misurataApri fonte ↗

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

   51stelle GitHub+1 (+2.0 %)
9. 9

   boundary-bench

   Agente

   AttivoUltimo commit 3 giorni fa · 2026-09-02

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

   TypeScriptLicenza: Apache-2.0

   • a2a
   • agent-evaluation
   • ai-agents
   • benchmark
   • deterministic-replay

   githubcreato 46 giorni facrescita misurataApri fonte ↗

   1stelle GitHubstabile
10. 10

    nora

    MCP

    AttivoUltimo commit oggi · 2026-09-06

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

    TypeScriptLicenza: Apache-2.0

    • agent-management
    • agent-ops
    • agent-orchestration
    • ai-agent-platform
    • ai-agents

    githubcreato 5 mesi facrescita misurataApri fonte ↗

    50stelle GitHub+1 (+2.0 %)
11. 11

    pyxen

    Agente

    AttivoUltimo commit 2 mesi fa · 2026-06-28

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

    PythonLicenza: MIT

    • a2a
    • agent-runtime
    • agents
    • observability
    • portability

    githubcreato 2 mesi facrescita misurataApri fonte ↗

    1stelle GitHubstabile
12. 12

    claudestat

    Skill

    AttivoUltimo commit 4 giorni fa · 2026-09-02

    Real-time execution trace and cost intelligence for Claude Code

    TypeScriptLicenza: MIT

    • agentic-workflow
    • ai-productivity
    • anthropic
    • anthropic-claude
    • claude

    githubcreato 4 mesi facrescita misurataApri fonte ↗

    Installa /plugin marketplace add DeibyGS/claudestat

    34stelle GitHubstabile
13. 13

    kaggle-capstone-ai-agent

    Agente

    DormienteUltimo commit 9 mesi fa · 2025-11-26

    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

    githubcreato 9 mesi facrescita misurataApri fonte ↗

    1stelle GitHubstabile
14. 14

    opus-fable-playbook

    Skill

    AttivoUltimo commit 2 mesi fa · 2026-07-03

    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.

    ShellLicenza: MIT

    • anthropic
    • claude
    • claude-code
    • claude-code-plugin
    • evals

    githubcreato 2 mesi facrescita misurataApri fonte ↗

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

    34stelle GitHub+1 (+3.0 %)
15. 15

    agentgateway

    MCP

    AttivoUltimo commit 1 giorno fa · 2026-09-04

    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…

    • agent-to-agent
    • ai-gateway
    • api-gateway
    • apis-json
    • cncf

    githubcreato 5 mesi facrescita misurataApri fonte ↗

    0stelle GitHubstabile
16. 16

    a2a-otel-kit

    MCP

    AttivoUltimo commit 25 giorni fa · 2026-08-11

    Vendor-neutral OpenTelemetry tracing for A2A agents and MCP services, with W3C context propagation and privacy-safe telemetry.

    PythonLicenza: MIT

    • a2a
    • agent2agent
    • agentic-ai
    • ai-agents
    • clean-architecture

    githubcreato 52 giorni facrescita misurataApri fonte ↗

    1stelle GitHubstabile
17. 17

    OpenJudge

    Skill

    AttivoUltimo commit 34 giorni fa · 2026-08-03

    OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

    PythonLicenza: Apache-2.0

    • agent
    • agent-skills
    • ai-agent
    • alignment
    • evaluation

    githubcreato 14 mesi facrescita misurataApri fonte ↗

    Installa git clone https://github.com/agentscope-ai/OpenJudge ~/.claude/skills/OpenJudge

    817stelle GitHub+10 (+1.2 %)
18. 18

    agent-stack

    Skill

    AttivoUltimo commit 4 giorni fa · 2026-09-01

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

    PythonLicenza: MIT

    • a2a
    • agent-orchestration
    • agent-skills
    • ai-agents
    • developer-tools

    githubcreato 31 giorni facrescita misurataApri fonte ↗

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

    2stelle GitHubstabile
19. 19

    langsmith-fetch-skill

    Skill

    DormienteUltimo commit 5 mesi fa · 2026-04-06

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

    Licenza: MIT

    • agent-debugging
    • ai-agents
    • claude-skills
    • claude-skills-creator
    • claude-skills-hub

    githubcreato 8 mesi facrescita misurataApri fonte ↗

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

    27stelle GitHubstabile
20. 20

    CustoFlow

    Altro

    DormienteUltimo commit 3 mesi fa · 2026-06-04

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

    PythonLicenza: MIT

    • a2a-protocol
    • agent-evaluation
    • google-adk
    • multi-agent-system
    • observability

    githubcreato 9 mesi facrescita misurataApri fonte ↗

    2stelle GitHubstabile
21. 21

    astragraph

    Agente

    DormienteUltimo commit 5 mesi fa · 2026-03-16

    Policy-enforced observability and fail-closed guardrails for MCP/A2A multi-agent systems.

    Rust

    • a2a
    • ai-agents
    • llm-security
    • mcp
    • multi-agent

    githubcreato 7 mesi facrescita misurataApri fonte ↗

    26stelle GitHubstabile
22. 22

    Agents-eval

    Agente

    DormienteUltimo commit 3 mesi fa · 2026-05-17

    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.

    PythonLicenza: Apache-2.0

    • a2a-protocol
    • agent-evaluation
    • agentbeats
    • ai-agents
    • benchmarks

    githubcreato 19 mesi facrescita misurataApri fonte ↗

    2stelle GitHubstabile
23. 23

    sentry-instrumentation

    Skill

    AttivoUltimo commit 2 mesi fa · 2026-06-19

    Sentry instrumentation skill for system-behavior tracking

    ShellLicenza: MIT

    • agent-skills
    • claude-skills
    • codex-skill
    • instrumentation
    • monitoring

    githubcreato 4 mesi facrescita misurataApri fonte ↗

    Installa git clone https://github.com/tortastudios/sentry-instrumentation ~/.claude/skills/sentry-instrumentation

    24stelle GitHubstabile
24. 24

    supervisor-skill-claude

    Skill

    AttivoUltimo commit 22 giorni fa · 2026-08-14

    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

    githubcreato 22 giorni fanuovocrescita misurataApri fonte ↗

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

    2stelle GitHubstabile
25. 25

    opik-claude-code-plugin

    MCP

    AttivoUltimo commit 37 giorni fa · 2026-07-30

    Log Claude Code sessions to Opik, the open-source LLM observability and evaluation platform, built by Comet. Tracing, evaluation, and skills for observable AI applications.

    GoLicenza: Apache-2.0

    • ai-agent
    • claude-ai
    • claude-code-plugin
    • llm-observation
    • mcp-server

    githubcreato 6 mesi facrescita misurataApri fonte ↗

    22stelle GitHub+1 (+4.8 %)