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

   SkillCorpus

   Skill

   AttivoUltimo commit 1 giorno fa · 2026-09-01

   Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.

   PythonLicenza: Apache-2.0

   • agent-memory
   • agent-skills
   • ai-agents
   • benchmark
   • dataset

   githubcreato 22 giorni fanuovocrescita misurataApri fonte ↗

   Installa git clone https://github.com/EverMind-AI/SkillCorpus ~/.claude/skills/SkillCorpus

   424stelle GitHub+204 (+92.7 %)
2. 2

   SkillEvaluator

   Skill

   AttivoUltimo commit oggi · 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+63 (+19.3 %)
3. 3

   craft-skills

   Skill

   AttivoUltimo commit 10 giorni fa · 2026-08-22

   Research-backed, eval-driven skills for AI agents

   PythonLicenza: Apache-2.0

   • agent-skills
   • ai-agents
   • codex
   • design
   • evals

   githubcreato 29 giorni fanuovocrescita misurataApri fonte ↗

   Installa git clone https://github.com/ZSeven-W/craft-skills ~/.claude/skills/craft-skills

   142stelle GitHub+21 (+17.4 %)
4. 4

   agent-kernel

   Agente

   AttivoUltimo commit oggi · 2026-09-01

   The Operating System for Scalable Enterprise AI Agents - Run, orchestrate, and deploy Compliant Enterprise AI Agents at scale across frameworks, without lock-in, rewrites or fragile glue code. Native support for MCP, A2A. Interface with all…

   PythonLicenza: Apache-2.0

   • a2a
   • adk
   • ai-agents
   • aws
   • azure

   githubcreato 13 mesi facrescita misurataApri fonte ↗

   156stelle GitHub+22 (+16.4 %)
5. 5

   skill-eval-harness

   Skill

   AttivoUltimo commit 2 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 %)
6. 6

   dynatrace-for-ai

   Skill

   AttivoUltimo commit 2 giorni fa · 2026-08-31

   Skills, prompts, and instructions for building AI agents on top of Dynatrace production context

   JavaScriptLicenza: Apache-2.0

   • agent-skills
   • ai-agents
   • claude-code
   • devops
   • dql

   githubcreato 5 mesi facrescita misurataApri fonte ↗

   Installa git clone https://github.com/Dynatrace/dynatrace-for-ai ~/.claude/skills/dynatrace-for-ai

   132stelle GitHub+6 (+4.8 %)
7. 7

   opentelemetry-agent-skills

   Skill

   AttivoUltimo commit oggi · 2026-09-01

   Vendor-neutral OpenTelemetry skills for AI coding agents, grounded in upstream sources

   ShellLicenza: Apache-2.0

   • agent-skills
   • ai
   • observability
   • opentelemetry

   githubcreato 5 mesi facrescita misurataApri fonte ↗

   Installa git clone https://github.com/ollygarden/opentelemetry-agent-skills ~/.claude/skills/opentelemetry-agent-skills

   97stelle GitHub+4 (+4.3 %)
8. 8

   databuff

   Agente

   AttivoUltimo commit 1 giorno fa · 2026-09-01

   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 ↗

   634stelle GitHub+26 (+4.3 %)
9. 9

   yao-meta-skill

   Skill

   AttivoUltimo commit 16 giorni fa · 2026-08-17

   YAO = Yielding AI Outcomes. A rigorous engineering, evaluation, governance, and portability system for reusable agent skills.

   PythonLicenza: MIT

   • agent-skills
   • ai-agents
   • evaluation
   • governance
   • meta-skill

   githubcreato 5 mesi facrescita misurataApri fonte ↗

   Installa git clone https://github.com/yaojingang/yao-meta-skill ~/.claude/skills/yao-meta-skill

   2 577stelle GitHub+54 (+2.1 %)
10. 10

    agent-skills-eval

    Skill

    AttivoUltimo commit 27 giorni fa · 2026-08-05

    A test runner for agentskills.io-style AI agent skills

    TypeScriptLicenza: MIT

    • agent-evals
    • agent-skills
    • agentskills
    • ai-agents
    • cli

    githubcreato 3 mesi facrescita misurataApri fonte ↗

    Installa git clone https://github.com/darkrishabh/agent-skills-eval ~/.claude/skills/agent-skills-eval

    719stelle GitHub+15 (+2.1 %)
11. 11

    trpc-agent-go

    MCP

    AttivoUltimo commit oggi · 2026-09-01

    A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.

    GoLicenza: Apache-2.0

    • a2a
    • a2a-protocol
    • ag-ui
    • agent
    • agent-framework

    githubcreato 15 mesi facrescita misurataApri fonte ↗

    1 759stelle GitHub+24 (+1.4 %)
12. 12

    skill-kit

    Skill

    AttivoUltimo commit 1 giorno fa · 2026-08-31

    local-first analytics for AI agent skills

    TypeScript

    • agent-skills
    • analytics
    • bun
    • claude-code
    • cli

    githubcreato 6 mesi facrescita misurataApri fonte ↗

    Installa git clone https://github.com/crafter-station/skill-kit ~/.claude/skills/skill-kit

    77stelle GitHub+1 (+1.3 %)
13. 13

    agent-skill-creator

    Skill

    AttivoUltimo commit 1 giorno fa · 2026-09-01

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

    PythonLicenza: MIT

    • agent-skills
    • ai-agents
    • claude-code
    • codex
    • cursor

    githubcreato 10 mesi facrescita misurataApri fonte ↗

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

    2 367stelle GitHub+30 (+1.3 %)
14. 14

    langfuse-docs

    Skill

    AttivoUltimo commit oggi · 2026-09-02

    🪢 Langfuse documentation -- Langfuse is the open source LLM Engineering Platform. Observability, evals, prompt management, playground and metrics to debug and improve LLM apps

    MDXLicenza: MIT

    • agent-skills
    • agents
    • genai
    • hacktoberfest
    • langfuse

    githubcreato 3 anni facrescita misurataApri fonte ↗

    Installa git clone https://github.com/langfuse/langfuse-docs ~/.claude/skills/langfuse-docs

    239stelle GitHub+3 (+1.3 %)
15. 15

    OpenJudge

    Skill

    AttivoUltimo commit 29 giorni fa · 2026-08-03

    OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

    PythonLicenza: Apache-2.0

    • agent
    • agent-skills
    • ai-agent
    • alignment
    • evaluation

    githubcreato 14 mesi facrescita misurataApri fonte ↗

    Installa git clone https://github.com/agentscope-ai/OpenJudge ~/.claude/skills/OpenJudge

    809stelle GitHub+10 (+1.3 %)
16. 16

    altk-evolve

    MCP

    AttivoUltimo commit 7 giorni fa · 2026-08-25

    Self improving agents through iterations

    PythonLicenza: Apache-2.0

    • agent-learning
    • agent-memory
    • agentic-workflows
    • ai-agents
    • claude-code

    githubcreato 8 mesi facrescita misurataApri fonte ↗

    105stelle GitHub+1 (+0.96 %)
17. 17

    claude-code-karma

    Skill

    AttivoUltimo commit 3 giorni fa · 2026-08-30

    Dashboard for monitoring claude code sessions.

    PythonLicenza: Apache-2.0

    • agents
    • agentskills
    • claude-code
    • claude-code-plugin
    • claude-code-skills

    githubcreato 7 mesi facrescita misurataApri fonte ↗

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

    323stelle GitHub+3 (+0.94 %)
18. 18

    fable-method

    Skill

    AttivoUltimo commit 48 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 57 giorni facrescita misurataApri fonte ↗

    Installa git clone https://github.com/Sahir619/fable-method ~/.claude/skills/fable-method

    2 272stelle GitHub+19 (+0.84 %)
19. 19

    adlc-team-skills

    Skill

    AttivoUltimo commit 13 giorni fa · 2026-08-20

    🐙 ADLC Team Skills — Agentic SDLC for Engineering Teams

    ShellLicenza: MIT

    • adr
    • agent-skills
    • agentic-sdlc
    • ai-coding
    • developer-tools

    githubcreato 43 giorni facrescita misurataApri fonte ↗

    Installa git clone https://github.com/tikalk/adlc-team-skills ~/.claude/skills/adlc-team-skills

    132stelle GitHub+1 (+0.76 %)
20. 20

    openobserve

    Altro

    AttivoUltimo commit oggi · 2026-09-02

    Open source observability platform for logs, metrics, traces, frontend monitoring, pipelines and LLM observability. A sophisticated, simple and highly performant alternative to Datadog, Splunk, and Elasticsearch with 140x lower storage…

    TypeScriptLicenza: AGPL-3.0

    • analytics
    • apm
    • datadog
    • elasticsearch
    • grafana

    githubcreato 3 anni facrescita misurataApri fonte ↗

    21 608stelle GitHub+115 (+0.54 %)
21. 21

    promptfoo

    Altro

    AttivoUltimo commit oggi · 2026-09-02

    Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI…

    TypeScriptLicenza: MIT

    • ci
    • ci-cd
    • cicd
    • evaluation
    • evaluation-framework

    githubcreato 3 anni facrescita misurataApri fonte ↗

    24 738stelle GitHub+131 (+0.53 %)
22. 22

    garak

    Altro

    AttivoUltimo commit 7 giorni fa · 2026-08-25

    the LLM vulnerability scanner

    PythonLicenza: Apache-2.0

    • ai
    • llm-evaluation
    • llm-security
    • security-scanners
    • vulnerability-assessment

    githubcreato 3 anni facrescita misurataApri fonte ↗

    9 079stelle GitHub+43 (+0.48 %)
23. 23

    mastra

    Altro

    AttivoUltimo commit oggi · 2026-09-02

    Mastra is the modern TypeScript framework for AI-powered applications and agents.

    TypeScript

    • agents
    • ai
    • chatbots
    • evals
    • javascript

    githubcreato 2 anni facrescita misurataApri fonte ↗

    27 624stelle GitHub+121 (+0.44 %)
24. 24

    SkillForge

    Skill

    AttivoUltimo commit 34 giorni fa · 2026-07-29

    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.

    PythonLicenza: MIT

    • agent-skills
    • claude-ai
    • claude-code
    • claude-skills
    • codex

    githubcreato 8 mesi facrescita misurataApri fonte ↗

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

    884stelle GitHub+3 (+0.34 %)
25. 25

    openstatus

    MCP

    AttivoUltimo commit 1 giorno fa · 2026-09-01

    🫖 Status page with uptime monitoring & API monitoring as code 🫖

    TypeScriptLicenza: AGPL-3.0

    • alerting
    • incident-management
    • mcp
    • mcp-server
    • monitoring

    githubcreato 3 anni facrescita misurataApri fonte ↗

    9 052stelle GitHub+28 (+0.31 %)