Le descrizioni degli strumenti sono in inglese.

Osservabilità LLM

Monitoraggio, tracce, valutazione e qualità delle applicazioni LLM.

118

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
AI Guardian
MCP
AttivoUltimo commit 8 giorni fa · 2026-08-26
Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.
PythonLicenza: MIT
mcpcreato 53 giorni facrescita misurataApri fonte ↗
Installa claude mcp add ai-guardian -- uvx ai-guardian-aiops
0stelle GitHubstabile
2
Flawless
Altro
AttivoUltimo commit 20 giorni fa · 2026-08-14
AI SRE AgenticOps for Kubernetes and cloud infrastructure.
Python
- agenticops
- ai
- aiops
- aisre
- cloud
githubcreato 55 giorni facrescita misurataApri fonte ↗
782stelle GitHub+1 (+0.13 %)
3
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
4
bakeoff
Skill
AttivoUltimo commit 55 giorni fa · 2026-07-09
Turn one decision into a judged tournament of solutions, then pick the best — a Claude Code skill that generates candidates, auto-derives the rubric, judges independently, and returns a defensible winner.
JavaScriptLicenza: MIT
- ai-agents
- anthropic
- claude-code
- claude-code-plugin
- claude-skill
githubcreato 58 giorni facrescita misurataApri fonte ↗
Installa /plugin marketplace add CoriChui/bakeoff
10stelle GitHubstabile
5
fable-method
Skill
AttivoUltimo commit 50 giorni fa · 2026-07-15
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.
PythonLicenza: MIT
- agent-skills
- ai-agents
- claude
- claude-code
- claude-md
githubcreato 58 giorni facrescita misurataApri fonte ↗
Installa git clone https://github.com/Sahir619/fable-method ~/.claude/skills/fable-method
2 272stelle GitHub+16 (+0.71 %)
6
rocketplaneIO
Altro
AttivoUltimo commit 36 giorni fa · 2026-07-29
Self-hosted AI SRE for Kubernetes — zero-instrumentation eBPF observability plus a copilot that fixes issues through guardrailed, self-verifying actions. BYO-LLM, air-gapped capable.
GoLicenza: Apache-2.0
- ai-agent
- aiops
- clickhouse
- devops
- ebpf
githubcreato 59 giorni facrescita misurataApri fonte ↗
131stelle GitHub-4 (-3.0 %)
7
seo-skill-bench
Skill
AttivoUltimo commit 12 giorni fa · 2026-08-21
Open benchmark for Claude Code SEO skills — real headless execution against fixture sites with planted-defect answer keys. Deterministic scoring, pre-registered rubric.
JavaScriptLicenza: MIT
- aeo
- agent-skills
- ai
- ai-seo
- benchmark
githubcreato 2 mesi facrescita misurataApri fonte ↗
Installa git clone https://github.com/aleclindz/seo-skill-bench ~/.claude/skills/seo-skill-bench
51stelle GitHub-5 (-8.9 %)
8
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
9
agentic-engineering-marketplace
Skill
AttivoUltimo commit 36 giorni fa · 2026-07-29
Claude Code plugin marketplace — agentic-engineering (spec-driven shape→decide→execute→measure→eval with adversarial review) + github-keeper (audit/elevate READMEs and make a repo open-source-ready).
PythonLicenza: MIT
- adr
- agentic-engineering
- ai-agents
- anthropic
- claude-code
githubcreato 2 mesi facrescita misurataApri fonte ↗
Installa /plugin marketplace add GiustoPiedimonte/agentic-engineering-marketplace
13stelle GitHubstabile
10
untell
Altro
AttivoUltimo commit 1 giorno fa · 2026-09-02
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…
PythonLicenza: MIT
- ai-detection
- ai-detector
- benchmark
- claude-code
- claude-code-skill
githubcreato 2 mesi facrescita misurataApri fonte ↗
18stelle GitHubstabile
11
SkillEvaluator
Skill
AttivoUltimo commit 2 giorni fa · 2026-09-01
Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.
PythonLicenza: Apache-2.0
- agent-evaluation
- agent-security
- agent-skills
- agentic-ai
- benchmark
githubcreato 2 mesi facrescita misurataApri fonte ↗
Installa git clone https://github.com/NVIDIA/SkillEvaluator ~/.claude/skills/SkillEvaluator
389stelle GitHub+57 (+17.2 %)
12
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
13
databuff
Agente
AttivoUltimo commit 1 giorno fa · 2026-09-02
DataBuff is an AI-native APM built on Opentelemetry，with multi-agent troubleshooting out of the box.
JavaLicenza: AGPL-3.0
- aiops
- apm
- application-monitoring
- devops
- distributed-tracing
githubcreato 2 mesi facrescita misurataApri fonte ↗
642stelle GitHub+32 (+5.2 %)
14
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
15
shokunin-review
Altro
AttivoUltimo commit 2 mesi fa · 2026-06-25
Terminal-first validation harness for reviewing PRDs, RFCs, strategy docs, and experiment plans.
TypeScript
- ai-agents
- claude-code
- claude-code-skills
- cli
- evals
githubcreato 2 mesi facrescita misurataApri fonte ↗
1stelle GitHubstabile
16
cap-evolve
MCP
AttivoUltimo commit 7 giorni fa · 2026-08-27
Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.
PythonLicenza: Apache-2.0
- agent-optimization
- agent-skills
- agentic-ai
- ai-agents
- claude
githubcreato 2 mesi facrescita misurataApri fonte ↗
47stelle GitHub+1 (+2.2 %)
17
pyxen
Agente
AttivoUltimo commit 2 mesi fa · 2026-06-28
A lightweight Python library that decouples agentic runtime from applications it builds
PythonLicenza: MIT
- a2a
- agent-runtime
- agents
- observability
- portability
githubcreato 2 mesi facrescita misurataApri fonte ↗
1stelle GitHubstabile
18
skill-eval-harness
Skill
AttivoUltimo commit 3 giorni fa · 2026-08-31
Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters
PythonLicenza: MIT
- agent-skills
- evals
- python
- skills
githubcreato 2 mesi facrescita misurataApri fonte ↗
Installa git clone https://github.com/adewale/skill-eval-harness ~/.claude/skills/skill-eval-harness
73stelle GitHub+4 (+5.8 %)
19
tulip-agents
Agente
AttivoUltimo commit 7 giorni fa · 2026-08-26
The 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…
PythonLicenza: Apache-2.0
- a2a
- agent-framework
- ai-agents
- ai-governance
- ai-safety
githubcreato 2 mesi facrescita misurataApri fonte ↗
1stelle GitHubstabile
20
axiom
Skill
AttivoUltimo commit 3 giorni fa · 2026-08-31
Axiom is a curated marketplace of shared plugins for Claude Code and Codex.
PythonLicenza: MIT
- agent-skills
- anthropic
- claude
- claude-code
- claude-code-marketplace
githubcreato 2 mesi facrescita misurataApri fonte ↗
Installa git clone https://github.com/netopsengineer/axiom ~/.claude/skills/axiom
5stelle GitHubstabile
21
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
22
anchor
Skill
AttivoUltimo commit 14 giorni fa · 2026-08-20
Anchor — the production-grade AGENTS.md template for AI coding agents. 51 sections of battle-tested rules. Keep your agents grounded.
Licenza: MIT
- agent-instructions
- agents-md
- ai-agent-instructions
- ai-coding
- ai-coding-agent
githubcreato 3 mesi facrescita misurataApri fonte ↗
Installa git clone https://github.com/peva3/anchor ~/.claude/skills/anchor
8stelle GitHubstabile

Risorse didattiche e di riferimento

Ranked by creation date, newest first; undated entries come last. Queste risorse restano accessibili separatamente e non partecipano alla classifica principale.

1
awesome-llm-observability
Skill
AttivoUltimo commit 3 giorni fa · 2026-08-31Apri 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.
Python
- ai-agents
- ai-engineering
- ai-observability
- awesome
- awesome-list
github
Installa git clone https://github.com/ContextJet-ai/awesome-llm-observability ~/.claude/skills/awesome-llm-observability
attivo 3 giorni facreato 2 mesi faRisorsacrescita misurata
32stelle GitHub+2 (+6.7 %)
2
awesome-agentic-devops
MCP
AttivoUltimo commit 2 giorni fa · 2026-09-01Apri 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.
PythonLicenza: MIT
- agent-skills
- agentic-ai
- agentic-devops
- ai-agents
- awesome
githubattivo 2 giorni facreato 2 mesi faRisorsacrescita misurata
77stelle GitHubstabile
3
tunelab
Skill
AttivoUltimo commit 40 giorni fa · 2026-07-25Apri fonte ↗
Claude Code plugin for LLM fine-tuning, distillation, and evaluation — decide whether you need fine-tuning at all, distill your LLM logs into small local models (MLX/LoRA), evaluate with held-out discipline, and learn the why at every step.
PythonLicenza: MIT
- claude-code
- claude-code-plugin
- distillation
- fine-tuning
- llm-evaluation
github
Installa /plugin marketplace add rchaz/tunelab
attivo 40 giorni facreato 2 mesi faRisorsacrescita misurata
6stelle GitHubstabile

Osservabilità LLM

Utilizzo

Attività

Ordina per

Classifica degli strumenti

AI Guardian

Flawless

homestream

bakeoff

fable-method

rocketplaneIO

seo-skill-bench

opus-fable-playbook

agentic-engineering-marketplace

untell

SkillEvaluator

DriftSentinel

databuff

historian

shokunin-review

cap-evolve

pyxen

skill-eval-harness

tulip-agents

axiom

DeepSeek-Infra

anchor

Risorse didattiche e di riferimento

awesome-llm-observability

awesome-agentic-devops

tunelab