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

   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
2. 2

   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
3. 3

   boundary-bench

   Agente

   AttivoUltimo commit 7 giorni fa · 2026-08-26

   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 43 giorni facrescita misurataApri fonte ↗

   1stelle GitHubstabile
4. 4

   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
5. 5

   DeepSeek-Infra

   Altro

   AttivoUltimo commit 1 giorno 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
6. 6

   primal-core

   Agente

   DormienteUltimo commit 3 mesi fa · 2026-05-18

   The reliability and interoperability layer for AI agents. A2A-native. MCP-bridged.

   PythonLicenza: Apache-2.0

   • a2a
   • agent-framework
   • agents
   • ai
   • ai-safety

   githubcreato 3 mesi facrescita misurataApri fonte ↗

   1stelle GitHubstabile
7. 7

   historian

   Agente

   AttivoUltimo commit 2 mesi fa · 2026-07-02

   A local A2A event and continuity service for agent applications, with structured history, provenance-safe transcripts, literal search, and natural-language queries.

   PythonLicenza: BSD-2-Clause

   • a2a
   • agent-memory
   • ai-agents
   • event-sourcing
   • fastapi

   githubcreato 2 mesi facrescita misurataApri fonte ↗

   1stelle GitHub+1
8. 8

   skill-adherencia-reglas

   Skill

   AttivoUltimo commit 33 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 37 giorni facrescita misurataApri fonte ↗

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

   1stelle GitHubstabile
9. 9

   adherencia-reglas

   Skill

   AttivoUltimo commit 33 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 37 giorni facrescita misurataApri fonte ↗

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

   1stelle GitHubstabile
10. 10

    agentanvil

    Agente

    DormienteUltimo commit 4 mesi fa · 2026-04-29

    Contract-based testing for LLM agents: hybrid evaluation, multi-agent + A2A, deterministic replay.

    PythonLicenza: MIT

    • a2a
    • agents
    • contracts
    • evaluation
    • llm

    githubcreato 4 mesi facrescita misurataApri fonte ↗

    0stelle GitHubstabile
11. 11

    mcp-smb-products

    MCP

    AttivoUltimo commit 2 mesi fa · 2026-07-03

    8 MCP SMB products — standalone AI servers for SMBs: Guardrails, FinOps, Observability, Router, Trust Score, Memory, ThinkSecure, A2A Lite. 37 tools, TNC credits billing.

    PythonLicenza: MIT

    • a2a-protocol
    • ai-governance
    • finops
    • guardrails
    • mcp

    githubcreato 4 mesi facrescita misurataApri fonte ↗

    1stelle GitHubstabile
12. 12

    CodeFlow

    Agente

    AttivoUltimo commit 6 giorni fa · 2026-08-28

    面向长程研发任务的 Java Agent Harness，支持 A2A 跨语言协作、可恢复执行、上下文工程与 Eval 驱动开发。

    JavaLicenza: Apache-2.0

    • a2a
    • agentic-ai
    • ai-agents
    • developer-tools
    • evals

    githubcreato 7 giorni fanuovocrescita misurataApri fonte ↗

    0stelle GitHubstabile
13. 13

    evoagent-os

    Agente

    AttivoUltimo commit 24 giorni fa · 2026-08-10

    Local-first control plane for durable, governed agent teams: DAG orchestration, approvals, memory, signed skills, trace contracts, and realtime.

    PythonLicenza: Apache-2.0

    • a2a-protocol
    • agentic-ai
    • ai-agents
    • fastapi
    • llmops

    githubcreato 24 giorni fanuovocrescita misurataApri fonte ↗

    0stelle GitHubstabile
14. 14

    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
15. 15

    homestream

    Altro

    AttivoUltimo commit 51 giorni fa · 2026-07-14

    🔑 HomeStream · 家园·流 — 零成本自托管多Agent协作框架，通往AI世界的那把钥匙 | Zero-cost self-hosted multi-agent framework — The key to AI world

    PythonLicenza: MIT

    • a2a-protocol
    • agent-framework
    • ai
    • causal-memory
    • event-stream

    githubcreato 55 giorni facrescita misurataApri fonte ↗

    0stelle GitHubstabile
16. 16

    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
17. 17

    nora

    MCP

    AttivoUltimo commit 2 giorni fa · 2026-09-01

    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+2 (+4.2 %)
18. 18

    claudestat

    Skill

    AttivoUltimo commit 3 giorni fa · 2026-08-30

    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 GitHub+1 (+3.0 %)
19. 19

    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

    33stelle GitHubstabile
20. 20

    agentgateway

    MCP

    AttivoUltimo commit 1 giorno fa · 2026-09-01

    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
21. 21

    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
22. 22

    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 6 mesi facrescita misurataApri fonte ↗

    26stelle GitHubstabile
23. 23

    otel-agent-provenance

    Agente

    DormienteUltimo commit 5 mesi fa · 2026-03-17

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

    Python

    • a2a-protocol
    • agentic-ai
    • ai-agents
    • observability
    • opentelemetry

    githubcreato 5 mesi facrescita misurataApri fonte ↗

    0stelle GitHubstabile
24. 24

    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
25. 25

    bar-observatory

    MCP

    AttivoUltimo commit 6 giorni fa · 2026-08-27

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

    HTMLLicenza: MIT

    • agent-monitoring
    • agentic-ai
    • ai-agents
    • ai-engineering
    • audit

    githubcreato 21 giorni fanuovocrescita misurataApri fonte ↗

    22stelle GitHub+2 (+10.0 %)