Le descrizioni degli strumenti sono in inglese.

Osservabilità LLM

Monitoraggio, tracce, valutazione e qualità delle applicazioni LLM.

Utilizzo

Attività

Ordina per

123

Classifica degli strumenti

Ranked by creation date, newest first; undated entries come last. I valori grezzi mantengono la propria finestra; una variazione richiede almeno due rilevazioni in 7 giorni.

  1. 1
    Dormiente

    A self-improving harness router for Claude Code.

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add SeongwoongCho/adaptive-harness

    8stelle GitHubstabile
  2. 2
    Dormiente

    OpenTelemetry semantic conventions and instrumentation for agent provenance, derivation lineage, and acceptance criteria evaluation. Fills the Microsoft AI stack observability gap.

    githubcrescita misurataApri fonte ↗

    0stelle GitHubstabile
  3. 3

    Skill
    Attivo

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

    githubcrescita misurataApri fonte ↗

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

    10stelle GitHub+1 (+11.1 %)
  4. 4
    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 %)
  5. 5

    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
  6. 6

    MCP
    Attivo

    AURA is a production-tested SRE agent platform you can deploy in minutes. AURA handles the guardrails, APIs, state management, streaming, and failure handling required to put AI to work safely on production infrastructure.

    githubcrescita misurataApri fonte ↗

    254stelle GitHub-3 (-1.2 %)
  7. 7

    MCP
    Dormiente

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

    githubcrescita misurataApri fonte ↗

    5stelle GitHubstabile
  8. 8

    Agente
    Dormiente

    AgentOps: Multi-agent infrastructure remediation platform. A2A protocol, agent coordination, HITL approval, auto-rollback.

    githubcrescita misurataApri fonte ↗

    0stelle GitHubstabile
  9. 9

    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 %)
  10. 10

    Altro
    Dormiente

    Official Python SDK for GT8004 — AI agent observability with MCP, A2A, x402 payment tracking. FastAPI, Flask, FastMCP middleware included.

    githubcrescita misurataApri fonte ↗

    1stelle GitHubstabile
  11. 11
    Attivo

    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.

    githubcrescita misurataApri fonte ↗

    22stelle GitHub+1 (+4.8 %)
  12. 12

    Agente
    Dormiente

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

    githubcrescita misurataApri fonte ↗

    26stelle GitHubstabile
  13. 13
    Dormiente

    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.

    githubcrescita misurataApri fonte ↗

    0stelle GitHubstabile
  14. 14

    Skill
    Attivo

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

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add shinpr/rashomon

    18stelle GitHubstabile
  15. 15
    Attivo

    Dashboard for monitoring claude code sessions.

    githubcrescita misurataApri fonte ↗

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

    323stelle GitHub+2 (+0.62 %)
  16. 16

    Skill
    Attivo

    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.

    githubcrescita misurataApri fonte ↗

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

    884stelle GitHub+1 (+0.11 %)
  17. 17
    Dormiente

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

    githubcrescita misurataApri fonte ↗

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

    27stelle GitHubstabile
  18. 18
    Attivo

    Self improving agents through iterations

    githubcrescita misurataApri fonte ↗

    105stelle GitHub+1 (+0.96 %)
  19. 19
    Dormiente

    An AI-powered multi-agent system that demonstrates clinical triage, OTC medication recommendations, and e-pharmacy integration for respiratory conditions. Built with modular agents that collaborate to provide safe, intelligent healthcare…

    githubcrescita misurataApri fonte ↗

    0stelle GitHubstabile
  20. 20
    Dormiente

    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)

    githubcrescita misurataApri fonte ↗

    1stelle GitHubstabile
  21. 21

    Altro
    Dormiente

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

    githubcrescita misurataApri fonte ↗

    2stelle GitHubstabile
  22. 22
    Dormiente

    Local open-source dev tool to debug, secure, and evaluate LLM agents. Provides static analysis, dynamic security checks, and runtime monitoring - integrates with Cursor and Claude Code.

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add cylestio/agent-inspector

    9stelle GitHubstabile
  23. 23
    Attivo

    Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.

    githubcrescita misurataApri fonte ↗

    Installa git clone https://github.com/FrancyJGLisboa/agent-skill-creator ~/.claude/skills/agent-skill-creator

    2 367stelle GitHub+28 (+1.2 %)
  24. 24

    Agente
    Attivo

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

    githubcrescita misurataApri fonte ↗

    0stelle GitHubstabile
  25. 25
    Dormiente

    MCP as a Judge: a behavioral MCP that strengthens AI coding assistants via explicit LLM evaluations

    mcpcrescita misurataApri fonte ↗

    Installa claude mcp add mcp-as-a-judge -- uvx mcp-as-a-judge

    17stelle GitHubstabile