Le descrizioni degli strumenti sono in inglese.

Osservabilità LLM

Monitoraggio, tracce, valutazione e qualità delle applicazioni LLM.

121

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
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
2
supervisor-skill-claude
Skill
AttivoUltimo commit 23 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 23 giorni fanuovocrescita misurataApri fonte ↗
Installa git clone https://github.com/ma-nucho-pro/supervisor-skill-claude ~/.claude/skills/supervisor-skill-claude
2stelle GitHubstabile
3
opik-claude-code-plugin
MCP
AttivoUltimo commit 38 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 GitHubstabile
4
bakeoff
Skill
AttivoUltimo commit 59 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
5
skill-graveyard
Skill
AttivoUltimo commit 58 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
6
agent-stack
Skill
AttivoUltimo commit oggi · 2026-09-06
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
7
axiom
Skill
AttivoUltimo commit 6 giorni fa · 2026-08-31
Axiom is a curated marketplace of shared plugins for Claude Code and Codex.
PythonLicenza: MIT
- agent-skills
- anthropic
- claude
- claude-code
- claude-code-marketplace
githubcreato 3 mesi facrescita misurataApri fonte ↗
Installa git clone https://github.com/netopsengineer/axiom ~/.claude/skills/axiom
5stelle GitHubstabile
8
dsh-plugins
Agente
AttivoUltimo commit 2 giorni fa · 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 19 giorni fanuovocrescita misurataApri fonte ↗
1stelle GitHubstabile
9
Agent-Reliability-and-Evaluation-Lab
MCP
AttivoUltimo commit 17 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 19 giorni fanuovocrescita misurataApri fonte ↗
3stelle GitHubstabile
10
rashomon
Skill
AttivoUltimo commit 7 giorni fa · 2026-08-30
Measure prompt and skill improvements with blind A/B comparison.
PythonLicenza: MIT
- agent-skills
- ai-tools
- claude-code
- claude-code-plugin
- claude-code-skill
githubcreato 7 mesi facrescita misurataApri fonte ↗
Installa /plugin marketplace add shinpr/rashomon
18stelle GitHubstabile
11
langfuse-mcp
MCP
AttivoUltimo commit oggi · 2026-09-06
A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability
PythonLicenza: MIT
- agent-skills
- ai-agents
- claude-code
- codex
- developer-tools
githubcreato 17 mesi facrescita misurataApri fonte ↗
105stelle GitHubstabile
12
simple-output-styles
Skill
AttivoUltimo commit 2 giorni fa · 2026-09-05
Make Claude write clearly, for everyone.
PythonLicenza: 0BSD
- claude-code
- claude-code-plugin
- controlled-language
- llm-evaluation
- output-style
githubcreato 37 giorni facrescita misurataApri fonte ↗
Installa /plugin marketplace add stefanobaghino/simple-output-styles
16stelle GitHubstabile
13
agenttap
Agente
DormienteUltimo commit 5 mesi fa · 2026-04-05
Real-time debugging proxy for Agent2Agent (A2A) multi-agent systems
Licenza: MIT
- a2a
- agent2agent
- debugging
- debugging-tool
- developer-tools
githubcreato 5 mesi facrescita misurataApri fonte ↗
3stelle GitHubstabile
14
headsup
Skill
AttivoUltimo commit 19 giorni fa · 2026-08-18
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,…
ShellLicenza: MIT
- ai-workflow-observability
- claude-code
- claude-code-hooks
- claude-code-skill
- claude-code-skills
githubcreato 3 mesi facrescita misurataApri fonte ↗
Installa git clone https://github.com/wasulajr/headsup ~/.claude/skills/headsup
1stelle GitHubstabile
15
sc-prism-releases
Skill
AttivoUltimo commit 4 giorni fa · 2026-09-03
Run many AIs on one board and keep control of all of it. Deterministic code decides who acts — never a model. A privacy floor keeps sensitive work on your machine, your own tests decide what counts as done, and every action lands on a…
- a2a
- agent-orchestration
- agent-skills
- ai-agents
- ai-governance
githubcreato 4 giorni fanuovocrescita misurataApri fonte ↗
Installa git clone https://github.com/sandhusukhdeep2/sc-prism-releases ~/.claude/skills/sc-prism-releases
1stelle GitHubstabile
16
verdict-contract
Skill
AttivoUltimo commit 7 giorni fa · 2026-08-30
Your LLM reviewer said APPROVE. Did it? A structured verdict contract: prompt rule + parser + exit-code gate in one stdlib file, with the 42 counterexamples that forced every line. Free, MIT.
PythonLicenza: MIT
- agent-skills
- ai-agents
- ci
- claude-code
- claude-code-skills
githubcreato 33 giorni facrescita misurataApri fonte ↗
Installa git clone https://github.com/tonydzi/verdict-contract ~/.claude/skills/verdict-contract
2stelle GitHubstabile
17
skill-evaluation-graph
Skill
AttivoUltimo commit oggi · 2026-09-06
Description Evidence-driven evaluation, benchmarking, and verified repair for Agent Skills across Codex, Claude Code, Gemini CLI, and Antigravity.
PythonLicenza: MIT
- agent-skills
- agentic-ai
- ai-agents
- ai-evaluation
- ai-safety
githubcreato 2 giorni fanuovocrescita misurataApri fonte ↗
Installa git clone https://github.com/MaxLaurieHutchinson/skill-evaluation-graph ~/.claude/skills/skill-evaluation-graph
2stelle GitHubstabile

Risorse didattiche e di riferimento

Classifica mista: la crescita misurata ha la precedenza. Queste risorse restano accessibili separatamente e non partecipano alla classifica principale.

1
production-ai-engineering
Agente
AttivoUltimo commit 48 giorni fa · 2026-07-20Apri fonte ↗
Handbook técnico aberto sobre engenharia de IA em produção: ML tradicional, LLMs, RAG, agentes, segurança, observabilidade, FinOps e deployment.
Markdown
- a2a-protocol
- agentic-ai
- ai
- ai-agents
- ai-engineering
githubattivo 48 giorni facreato 3 mesi faRisorsacrescita misurata
1stelle GitHubstabile
2
trigger_tree
Skill
AttivoUltimo commit 6 giorni fa · 2026-09-01Apri fonte ↗
Documentation-discovery telemetry for Claude Code — heat/cold maps, health grade, evidence-backed router fixes. 100% local, zero tokens. /tt
PythonLicenza: MIT
- ai-agents
- claude-code
- claude-code-plugin
- docs-as-code
- documentation
github
Installa /plugin marketplace add Hedde/trigger_tree
attivo 6 giorni facreato 51 giorni faRisorsacrescita misurata
14stelle GitHubstabile
3
Agentic_AI_Engineer
Agente
AttivoUltimo commit 5 giorni fa · 2026-09-01Apri fonte ↗
My complete journey to becoming an Agentic AI Engineer through structured learning, projects, experiments, and production-ready implementations of modern AI systems.
Jupyter NotebookLicenza: MIT
- a2a-protocol
- agent-orchestration
- ai-guardrails
- fastapi
- kubernetes
githubattivo 5 giorni facreato 43 giorni faRisorsacrescita misurata
18stelle GitHubstabile
4
tunelab
Skill
AttivoUltimo commit 44 giorni fa · 2026-07-25Apri fonte ↗
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.
PythonLicenza: MIT
- claude-code
- claude-code-plugin
- distillation
- fine-tuning
- llm-evaluation
github
Installa /plugin marketplace add rchaz/tunelab
attivo 44 giorni facreato 2 mesi faRisorsamomentum stimato
6stelle GitHub·

Osservabilità LLM

Utilizzo

Attività

Ordina per

Classifica degli strumenti

pyxen

supervisor-skill-claude

opik-claude-code-plugin

bakeoff

skill-graveyard

agent-stack

axiom

dsh-plugins

Agent-Reliability-and-Evaluation-Lab

rashomon

langfuse-mcp

simple-output-styles

agenttap

headsup

sc-prism-releases

verdict-contract

skill-evaluation-graph

Risorse didattiche e di riferimento

production-ai-engineering

trigger_tree

Agentic_AI_Engineer

tunelab