Le descrizioni degli strumenti sono in inglese.

Osservabilità LLM

Monitoraggio, tracce, valutazione e qualità delle applicazioni LLM.

Utilizzo

Attività

Ordina per

75

Classifica degli strumenti

Ranked by known GitHub stars, highest first; archived repositories come after maintained repositories. I valori grezzi mantengono la propria finestra; una variazione richiede almeno due rilevazioni in 7 giorni.

  1. 1

    Agente
    Attivo

    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…

    githubcrescita misurataApri fonte ↗

    156stelle GitHub+19 (+13.9 %)
  2. 2

    Skill
    Attivo

    Research-backed, eval-driven skills for AI agents

    githubcrescita misurataApri fonte ↗

    Installa git clone https://github.com/ZSeven-W/craft-skills ~/.claude/skills/craft-skills

    142stelle GitHub+18 (+14.5 %)
  3. 3

    Altro
    Attivo

    Evidence-first infrastructure for reproducible, isolated executable evaluation and online rewards.

    githubcrescita misurataApri fonte ↗

    140stelle GitHub+24 (+20.7 %)
  4. 4
    Attivo

    🐙 ADLC Team Skills — Agentic SDLC for Engineering Teams

    githubcrescita misurataApri fonte ↗

    Installa git clone https://github.com/tikalk/adlc-team-skills ~/.claude/skills/adlc-team-skills

    132stelle GitHub+1 (+0.76 %)
  5. 5
    Attivo

    Skills, prompts, and instructions for building AI agents on top of Dynatrace production context

    githubcrescita misurataApri fonte ↗

    Installa git clone https://github.com/Dynatrace/dynatrace-for-ai ~/.claude/skills/dynatrace-for-ai

    132stelle GitHub+4 (+3.1 %)
  6. 6
    Attivo

    74 open-source Agent Skills for Claude Code and Codex: AI SEO, AEO and GEO, code review with an A-F ship grade, CI gates, AI evals, design systems, conversion copy, Instagram growth, iOS and Android app shipping, creator rights, and…

    githubcrescita misurataApri fonte ↗

    129stelle GitHub-4 (-3.0 %)
  7. 7
    Attivo

    A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability

    githubcrescita misurataApri fonte ↗

    105stelle GitHubstabile
  8. 8
    Attivo

    Self improving agents through iterations

    githubcrescita misurataApri fonte ↗

    105stelle GitHub+1 (+0.96 %)
  9. 9
    Attivo

    Vendor-neutral OpenTelemetry skills for AI coding agents, grounded in upstream sources

    githubcrescita misurataApri fonte ↗

    Installa git clone https://github.com/ollygarden/opentelemetry-agent-skills ~/.claude/skills/opentelemetry-agent-skills

    97stelle GitHub+4 (+4.3 %)
  10. 10

    Skill
    Attivo

    local-first analytics for AI agent skills

    githubcrescita misurataApri fonte ↗

    Installa git clone https://github.com/crafter-station/skill-kit ~/.claude/skills/skill-kit

    77stelle GitHub+1 (+1.3 %)
  11. 11
    Attivo

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

    githubcrescita misurataApri fonte ↗

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

    73stelle GitHub+4 (+5.8 %)
  12. 12
    Attivo

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

    githubcrescita misurataApri fonte ↗

    68stelle GitHubstabile
  13. 13

    Skill
    Attivo

    Deletion-first Agent Skill for removing test bloat, verification theater, and speculative fallbacks while preserving behavior.

    githubcrescita misurataApri fonte ↗

    Installa git clone https://github.com/MrZoyo/deslop-GPT ~/.claude/skills/deslop-GPT

    55stelle GitHub+27 (+96.4 %)
  14. 14
    Attivo

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

    githubcrescita misurataApri fonte ↗

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

    51stelle GitHub-5 (-8.9 %)
  15. 15

    MCP
    Attivo

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

    githubcrescita misurataApri fonte ↗

    50stelle GitHub+2 (+4.2 %)
  16. 16

    Skill
    Attivo

    Agent skills for Arize — datasets, experiments, and traces via the ax CLI

    githubcrescita misurataApri fonte ↗

    Installa git clone https://github.com/Arize-ai/arize-skills ~/.claude/skills/arize-skills

    47stelle GitHubstabile
  17. 17
    Attivo

    Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

    githubcrescita misurataApri fonte ↗

    47stelle GitHub+1 (+2.2 %)
  18. 18
    Attivo

    Mini Program Engineering Skill Suite is an Agent Skill suite for evidence‑first mini‑program development. It helps agents bring WeChat or other mini‑program projects from vague intent to reliable engineering work: project intake, product…

    githubmomentum stimatoApri fonte ↗

    Installa git clone https://github.com/NocodeMrLi/mini-program-engineering-skill-suite ~/.claude/skills/mini-program-engineering-skill-suite

    39stelle GitHub
  19. 19

    Skill
    Attivo

    Real-time execution trace and cost intelligence for Claude Code

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add DeibyGS/claudestat

    34stelle GitHub+1 (+3.0 %)
  20. 20
    Attivo

    Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.

    githubcrescita misurataApri fonte ↗

    22stelle GitHub+2 (+10.0 %)
  21. 21

    Skill
    Attivo

    Measure prompt and skill improvements with blind A/B comparison.

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add shinpr/rashomon

    18stelle GitHubstabile
  22. 22

    Altro
    Attivo

    AI-detector auditing toolkit: measures how often a detector flags genuine human writing, how stable its verdict is across seeds, and whether that verdict survives meaning-preserving edits. Detector-in-the-loop measurement harness. Claude…

    githubcrescita misurataApri fonte ↗

    18stelle GitHubstabile

Risorse didattiche e di riferimento

Ranked by known GitHub stars, highest first; archived repositories come after maintained repositories. Queste risorse restano accessibili separatamente e non partecipano alla classifica principale.

  1. 1
    AttivoApri fonte ↗

    Curated + scored map of official MCP servers and agents for DevOps, Cloud, SRE, and Platform Engineering — every entry rated on production access, approval gates, and audit evidence.

    githubRisorsacrescita misurata
    77stelle GitHubstabile
  2. 2
    AttivoApri fonte ↗

    50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.

    github

    Installa git clone https://github.com/ContextJet-ai/awesome-llm-observability ~/.claude/skills/awesome-llm-observability

    Risorsacrescita misurata
    32stelle GitHub+2 (+6.7 %)
  3. 3
    AttivoApri fonte ↗

    My complete journey to becoming an Agentic AI Engineer through structured learning, projects, experiments, and production-ready implementations of modern AI systems.

    githubRisorsacrescita misurata
    18stelle GitHubstabile