Le descrizioni degli strumenti sono in inglese.
Osservabilità LLM
Monitoraggio, tracce, valutazione e qualità delle applicazioni LLM.
Utilizzo
Attività
Ordina per
122
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.
- 1Attivo
dsh-plugins
AgenteGeneric DeepSeek Harness (dsh) plugins: A2A protocol server, session storage mirror, and Langfuse observability.
githubcrescita misurataApri fonte ↗
1stelle GitHubstabile - 2Attivo
nudge
MCPA typed, replayable, budget-aware programming language for LLM agents. Compiles to Python & TypeScript.
githubcrescita misurataApri fonte ↗
2stelle GitHubstabile - 3Attivo
skill-receipts
SkillClaude Code skills where every entry ships receipts — accuracy-gated benchmarks against baseline and placebo, rejects published
githubcrescita misurataApri fonte ↗
Installa
git clone https://github.com/sjh9714/skill-receipts ~/.claude/skills/skill-receipts2stelle GitHubstabile - 4Attivo
agent-stack
SkillProduction patterns for agent orchestrators, harnesses, evals, MCP/A2A interoperability, memory, provider routing, and LLM usage metering.
githubcrescita misurataApri fonte ↗
Installa
git clone https://github.com/ssheleg/agent-stack ~/.claude/skills/agent-stack2stelle GitHub+1 (+100.0 %) - 5Attivo
pyxen
AgenteA lightweight Python library that decouples agentic runtime from applications it builds
githubcrescita misurataApri fonte ↗
1stelle GitHubstabile - 6Attivo
Multi-agent quality gate skill for Claude Code that researches, reviews, tests and challenges AI-generated work before the final answer.
githubcrescita misurataApri fonte ↗
Installa
git clone https://github.com/ma-nucho-pro/supervisor-skill-claude ~/.claude/skills/supervisor-skill-claude2stelle GitHubstabile - 7Dormiente
CustoFlow
AltroMulti-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 - 8Dormiente
Agents-eval
AgenteA 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.
githubcrescita misurataApri fonte ↗
2stelle GitHubstabile - 9Attivo
boundary-bench
AgenteDeterministic crash tests for agent control planes: paired worlds, hard stops, budgets, scopes, approvals, and hash-linked receipts.
githubcrescita misurataApri fonte ↗
1stelle GitHubstabile - 10Attivo
DriftSentinel
AgenteAgent 降智检测与自愈公评网络 — an immune system for the AI agent society
githubcrescita misurataApri fonte ↗
1stelle GitHubstabile - 11Dormiente
kaggle-capstone-ai-agent
AgenteA 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 - 12Attivo
DeepSeek-Infra
AltroLocal-first Agentic AI Infrastructure Platform with LLM Gateway, Agent DAG Runtime, MCP Tool Hub, A2A Agent Mesh, Local RAG, Tool Sandbox and Observability.
githubcrescita misurataApri fonte ↗
1stelle GitHubstabile - 13Dormiente
primal-core
AgenteThe reliability and interoperability layer for AI agents. A2A-native. MCP-bridged.
githubcrescita misurataApri fonte ↗
1stelle GitHubstabile - 14Attivo
historian
AgenteA local A2A event and continuity service for agent applications, with structured history, provenance-safe transcripts, literal search, and natural-language queries.
githubcrescita misurataApri fonte ↗
1stelle GitHub+1 - 15Attivo
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.
githubcrescita misurataApri fonte ↗
Installa
/plugin marketplace add jleonceo/skill-adherencia-reglas1stelle GitHubstabile - 16Attivo
adherencia-reglas
SkillMide 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.
githubcrescita misurataApri fonte ↗
Installa
git clone https://github.com/jleonceo/adherencia-reglas ~/.claude/skills/adherencia-reglas1stelle GitHubstabile - 17Dormiente
agentanvil
AgenteContract-based testing for LLM agents: hybrid evaluation, multi-agent + A2A, deterministic replay.
githubcrescita misurataApri fonte ↗
0stelle GitHubstabile - 18Attivo
8 MCP SMB products — standalone AI servers for SMBs: Guardrails, FinOps, Observability, Router, Trust Score, Memory, ThinkSecure, A2A Lite. 37 tools, TNC credits billing.
githubcrescita misurataApri fonte ↗
1stelle GitHubstabile - 19Attivo
CodeFlow
Agente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。
githubcrescita misurataApri fonte ↗
0stelle GitHubstabile - 20Attivo
evoagent-os
AgenteLocal-first control plane for durable, governed agent teams: DAG orchestration, approvals, memory, signed skills, trace contracts, and realtime.
githubcrescita misurataApri fonte ↗
0stelle GitHubstabile - 21Attivo
green-agent
AgenteA2A green-agent orchestrator for evaluating agents on the AppWorld benchmark, built on the AgentBeats SDK
githubcrescita misurataApri fonte ↗
0stelle GitHubstabile - 22Attivo
homestream
Altro🔑 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
githubcrescita misurataApri fonte ↗
0stelle GitHubstabile - 23Dormiente
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 - 24Attivo
nora
MCPOpen-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 %) - 25Attivo
claudestat
SkillReal-time execution trace and cost intelligence for Claude Code
githubcrescita misurataApri fonte ↗
Installa
/plugin marketplace add DeibyGS/claudestat34stelle GitHub+1 (+3.0 %)