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

   AgentStack

   Agente

   AttivoUltimo commit 1 giorno fa · 2026-09-04

   Provide clear documentation for AgentStack’s MCP protocol, plugins, and ecosystem API with usage examples and tool references.

   • a2a
   • anthropic
   • claude-code
   • crewai
   • deep-learning

   githubcreato 5 mesi facrescita misurataApri fonte ↗

   0stelle GitHubstabile
2. 2

   AgentX-Python

   Altro

   AttivoUltimo commit 1 giorno fa · 2026-09-04

   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
3. 3

   Agent-Reliability-and-Evaluation-Lab

   MCP

   AttivoUltimo commit 15 giorni fa · 2026-08-21

   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…

   PythonLicenza: Apache-2.0

   • a2a-protocol
   • agent-to-agent
   • ai-agents
   • async-python
   • autoscaling

   githubcreato 17 giorni fanuovocrescita misurataApri fonte ↗

   3stelle GitHubstabile
4. 4

   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 %)
5. 5

   adherencia-reglas

   Skill

   AttivoUltimo commit 35 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 39 giorni facrescita misurataApri fonte ↗

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

   1stelle GitHubstabile
6. 6

   claudestat

   Skill

   AttivoUltimo commit 2 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
7. 7

   seo-skill-bench

   Skill

   AttivoUltimo commit 14 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-5 (-8.9 %)
8. 8

   skill-receipts

   Skill

   AttivoUltimo commit 36 giorni fa · 2026-07-30

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

   JavaScriptLicenza: MIT

   • agent-skills
   • ai-agents
   • anthropic
   • benchmark
   • claude

   githubcreato 45 giorni facrescita misurataApri fonte ↗

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

   2stelle GitHubstabile
9. 9

   green-agent

   Agente

   AttivoUltimo commit 2 mesi fa · 2026-07-01

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

   Python

   • a2a-protocol
   • agentbeats
   • appworld
   • evaluation
   • llm-agents

   githubcreato 11 mesi facrescita misurataApri fonte ↗

   0stelle GitHubstabile
10. 10

    SkillForge

    Skill

    AttivoUltimo commit 37 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 GitHubstabile
11. 11

    bakeoff

    Skill

    AttivoUltimo commit 57 giorni fa · 2026-07-09

    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.

    JavaScriptLicenza: MIT

    • ai-agents
    • anthropic
    • claude-code
    • claude-code-plugin
    • claude-skill

    githubcreato 2 mesi facrescita misurataApri fonte ↗

    Installa /plugin marketplace add CoriChui/bakeoff

    10stelle GitHubstabile
12. 12

    nora

    MCP

    AttivoUltimo commit oggi · 2026-09-04

    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 %)
13. 13

    yao-meta-skill

    Skill

    AttivoUltimo commit 19 giorni fa · 2026-08-17

    YAO = Yielding AI Outcomes. A rigorous engineering, evaluation, governance, and portability system for reusable agent skills.

    PythonLicenza: MIT

    • agent-skills
    • ai-agents
    • evaluation
    • governance
    • meta-skill

    githubcreato 5 mesi facrescita misurataApri fonte ↗

    Installa git clone https://github.com/yaojingang/yao-meta-skill ~/.claude/skills/yao-meta-skill

    2 596stelle GitHub+37 (+1.4 %)
14. 14

    skill-adherencia-reglas

    Skill

    AttivoUltimo commit 35 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 39 giorni facrescita misurataApri fonte ↗

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

    1stelle GitHubstabile
15. 15

    forge-skills

    Skill

    DormienteUltimo commit 3 mesi fa · 2026-05-21

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

    ShellLicenza: MIT

    • agentic-engineering
    • agents
    • claude-code
    • claude-code-plugin
    • claude-code-skills

    githubcreato 5 mesi facrescita misurataApri fonte ↗

    Installa /plugin marketplace add aneja5/forge-skills

    3stelle GitHubstabile
16. 16

    skill-graveyard

    Skill

    AttivoUltimo commit 56 giorni fa · 2026-07-10

    Audit which Claude Code skills you actually use — surface dead installs and hallucinated invocations from your session logs.

    TypeScriptLicenza: MIT

    • anthropic
    • audit
    • claude
    • claude-code
    • claude-code-plugin

    githubcreato 4 mesi facrescita misurataApri fonte ↗

    Installa /plugin marketplace add sfrangulov/skill-graveyard

    10stelle GitHubstabile
17. 17

    MLFlow-A2A-Session-Tracer

    Agente

    DormienteUltimo commit 4 mesi fa · 2026-04-15

    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.

    Python

    • a2a
    • agent-to-agent
    • ai-agents
    • conversational-ai
    • llm-evaluation

    githubcreato 7 mesi facrescita misurataApri fonte ↗

    0stelle GitHubstabile
18. 18

    ai-dev-stack

    Skill

    AttivoUltimo commit 2 mesi fa · 2026-06-29

    Production-grade AI coding rules for Cursor and Claude Code. 15 rules + 9 doc templates + skills + agents + MCP setup. Drop into any project.

    PythonLicenza: MIT

    • ai-agents
    • ai-coding
    • ai-development
    • ai-engineer
    • automation

    githubcreato 6 mesi facrescita misurataApri fonte ↗

    Installa git clone https://github.com/aiagentwithdhruv/ai-dev-stack ~/.claude/skills/ai-dev-stack

    10stelle GitHubstabile
19. 19

    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
20. 20

    claude-code-karma

    Skill

    AttivoUltimo commit 6 giorni fa · 2026-08-30

    Dashboard for monitoring claude code sessions.

    PythonLicenza: Apache-2.0

    • agents
    • agentskills
    • claude-code
    • claude-code-plugin
    • claude-code-skills

    githubcreato 8 mesi facrescita misurataApri fonte ↗

    Installa /plugin marketplace add JayantDevkar/claude-code-karma

    324stelle GitHub+3 (+0.93 %)
21. 21

    galdor

    Altro

    AttivoUltimo commit 12 giorni fa · 2026-08-24

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

    GoLicenza: Apache-2.0

    • a2a
    • agents
    • ai
    • anthropic
    • bedrock

    githubcreato 3 mesi facrescita misurataApri fonte ↗

    10stelle GitHubstabile
22. 22

    agent-kernel

    Agente

    AttivoUltimo commit oggi · 2026-09-04

    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…

    PythonLicenza: Apache-2.0

    • a2a
    • adk
    • ai-agents
    • aws
    • azure

    githubcreato 13 mesi facrescita misurataApri fonte ↗

    166stelle GitHub+25 (+17.7 %)
23. 23

    kiboserve

    MCP

    DormienteUltimo commit 4 mesi fa · 2026-04-25

    Open-source Python framework to deploy AI agents via HTTP, A2A, and MCP with built-in observability

    PythonLicenza: MIT

    • a2a
    • a2a-client
    • a2a-server
    • agent-evaluation
    • agentic-ai

    githubcreato 6 mesi facrescita misurataApri fonte ↗

    5stelle GitHubstabile
24. 24

    boundary-bench

    Agente

    AttivoUltimo commit 2 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 45 giorni facrescita misurataApri fonte ↗

    1stelle GitHubstabile
25. 25

    dsh-plugins

    Agente

    AttivoUltimo commit oggi · 2026-09-05

    Generic DeepSeek Harness (dsh) plugins: A2A protocol server, session storage mirror, and Langfuse observability.

    TypeScriptLicenza: MIT

    • agent2agent
    • ai-agents
    • cordis
    • deepseek-harness
    • dsh

    githubcreato 17 giorni fanuovocrescita misurataApri fonte ↗

    1stelle GitHubstabile