Le descrizioni degli strumenti sono in inglese.
Osservabilità LLM
Monitoraggio, tracce, valutazione e qualità delle applicazioni LLM.
Utilizzo
Attività
Ordina per
74
Classifica degli strumenti
Classifica mista: la crescita misurata ha la precedenza. I valori grezzi mantengono la propria finestra; una variazione richiede almeno due rilevazioni in 7 giorni.
- 1Attivo
rashomon
SkillMeasure prompt and skill improvements with blind A/B comparison.
githubcrescita misurataApri fonte ↗
Installa
/plugin marketplace add shinpr/rashomon18stelle GitHubstabile - 2Attivo
simple-output-styles
SkillMake Claude write clearly, for everyone.
githubcrescita misurataApri fonte ↗
Installa
/plugin marketplace add stefanobaghino/simple-output-styles16stelle GitHubstabile - 3Attivo
Query Spanlens LLM observability from Cursor, Claude Desktop, or Continue via MCP.
mcpcrescita misurataApri fonte ↗
Installa
claude mcp add mcp-server -- npx @spanlens/mcp-server12stelle GitHubstabile - 4Attivo
galdor
AltroA Go-native framework for LLM agents, with OpenTelemetry observability built in.
githubcrescita misurataApri fonte ↗
10stelle GitHubstabile - 5Attivo
anchor
SkillAnchor — the production-grade AGENTS.md template for AI coding agents. 51 sections of battle-tested rules. Keep your agents grounded.
githubcrescita misurataApri fonte ↗
Installa
git clone https://github.com/peva3/anchor ~/.claude/skills/anchor8stelle GitHubstabile - 6Attivo
memroos
AgenteMemroOS / memroos: memory OS and governance layer for AI agents, agent workflows, dispatch, proof, and context continuity.
githubcrescita misurataApri fonte ↗
7stelle GitHubstabile - 7Attivo
axiom
SkillAxiom is a curated marketplace of shared plugins for Claude Code and Codex.
githubcrescita misurataApri fonte ↗
Installa
git clone https://github.com/netopsengineer/axiom ~/.claude/skills/axiom5stelle GitHubstabile - 8Attivo
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…
githubcrescita misurataApri fonte ↗
3stelle GitHubstabile - 9Attivo
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 - 10Attivo
nudge
MCPA typed, replayable, budget-aware programming language for LLM agents. Compiles to Python & TypeScript.
githubcrescita misurataApri fonte ↗
2stelle GitHubstabile - 11Attivo
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 - 12Attivo
a2a-otel-kit
MCPVendor-neutral OpenTelemetry tracing for A2A agents and MCP services, with W3C context propagation and privacy-safe telemetry.
githubcrescita misurataApri fonte ↗
1stelle GitHubstabile - 13Attivo
headsup
SkillGlanceable 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,…
githubcrescita misurataApri fonte ↗
Installa
git clone https://github.com/wasulajr/headsup ~/.claude/skills/headsup1stelle GitHubstabile - 14Attivo
tulip-agents
AgenteThe agent framework where the model never holds the trigger — every consequential action clears your policy first, waits for a human when it matters, and lands on a record you can verify. Build on it, or put it around the agent you already…
githubcrescita misurataApri fonte ↗
1stelle GitHubstabile - 15Attivo
dsh-plugins
AgenteGeneric DeepSeek Harness (dsh) plugins: A2A protocol server, session storage mirror, and Langfuse observability.
githubcrescita misurataApri fonte ↗
1stelle GitHubstabile - 16Attivo
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 - 17Attivo
Architecture-first Python scaffold for an auditable multi-agent corporate credit desk using A2A, MCP, deterministic credit policies, model routing, and OpenTelemetry.
githubcrescita misurataApri fonte ↗
0stelle GitHubstabile - 18Attivo
AgentStack
AgenteProvide clear documentation for AgentStack’s MCP protocol, plugins, and ecosystem API with usage examples and tool references.
githubcrescita misurataApri fonte ↗
0stelle GitHubstabile - 19Attivo
agentgateway
MCPAgentGateway — 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…
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
AI Guardian
MCPGoverned local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.
mcpcrescita misurataApri fonte ↗
Installa
claude mcp add ai-guardian -- uvx ai-guardian-aiops0stelle GitHubstabile - 22Attivo
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 - 23Attivo
VeriRun
AltroEvidence-first infrastructure for reproducible, isolated executable evaluation and online rewards.
githubmomentum stimatoApri fonte ↗
116stelle GitHub—
Risorse didattiche e di riferimento
Classifica per crescita misurata e normalizzata tra le fonti. Queste risorse restano accessibili separatamente e non partecipano alla classifica principale.
- 1AttivoApri fonte ↗
Agentic_AI_Engineer
AgenteMy complete journey to becoming an Agentic AI Engineer through structured learning, projects, experiments, and production-ready implementations of modern AI systems.
githubRisorsacrescita misurata18stelle GitHubstabile