Le descrizioni degli strumenti sono in inglese.

Osservabilità LLM

Monitoraggio, tracce, valutazione e qualità delle applicazioni LLM.

Utilizzo

Attività

Ordina per

117

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

    Skill
    Dormiente

    Two Claude Code skills for adversarial code review (single-model PAR and multi-model MMAR with cross-critique to catch hallucinations), plus a fixture-based eval suite.

    Python
    • ai-agents
    • claude-code-plugin
    • code-review
    • evals
    • python

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add prime-radiant-inc/parallel-adversarial-review

    17stelle GitHubstabile
  2. 2

    Skill
    Dormiente

    An assembly line for AI software development. 35 skills, 11 agent personas, 29 commands. From raw idea to shipped code.

    ShellLicenza: MIT
    • agentic-engineering
    • agents
    • claude-code
    • claude-code-plugin
    • claude-code-skills

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add aneja5/forge-skills

    3stelle GitHubstabile
  3. 3

    Skill
    Attivo

    Make Claude write clearly, for everyone.

    PythonLicenza: 0BSD
    • claude-code
    • claude-code-plugin
    • controlled-language
    • llm-evaluation
    • output-style

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add stefanobaghino/simple-output-styles

    16stelle GitHubstabile
  4. 4

    Agente
    Attivo

    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

    githubcrescita misurataApri fonte ↗

    0stelle GitHubstabile
  5. 5

    MCP
    Attivo

    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…

    PythonLicenza: Apache-2.0
    • a2a-protocol
    • agent-to-agent
    • ai-agents
    • async-python
    • autoscaling

    githubcrescita misurataApri fonte ↗

    3stelle GitHubstabile
  6. 6

    Agente
    Dormiente

    Real-time debugging proxy for Agent2Agent (A2A) multi-agent systems

    Licenza: MIT
    • a2a
    • agent2agent
    • debugging
    • debugging-tool
    • developer-tools

    githubcrescita misurataApri fonte ↗

    3stelle GitHubstabile
  7. 7

    Skill
    Attivo

    Axiom is a curated marketplace of shared plugins for Claude Code and Codex.

    PythonLicenza: MIT
    • agent-skills
    • anthropic
    • claude
    • claude-code
    • claude-code-marketplace

    githubcrescita misurataApri fonte ↗

    Installa git clone https://github.com/netopsengineer/axiom ~/.claude/skills/axiom

    5stelle GitHubstabile
  8. 8

    Skill
    Attivo

    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

    githubcrescita misurataApri fonte ↗

    Installa /plugin marketplace add GiustoPiedimonte/agentic-engineering-marketplace

    13stelle GitHubstabile
  9. 9

    MCP
    Dormiente

    Open-source Python framework to deploy AI agents via HTTP, A2A, and MCP with built-in observability

    PythonLicenza: MIT
    • a2a
    • a2a-client
    • a2a-server
    • agent-evaluation
    • agentic-ai

    githubcrescita misurataApri fonte ↗

    5stelle GitHubstabile
  10. 10

    Altro
    Dormiente

    A Claude Code skill that adds a rubric-based eval layer to any agent project. Framework-agnostic — generates rubric, test cases, judge prompt, and harness. Returns a weighted score plus a judge-leniency signal.

    HTML
    • agent-evaluation
    • anthropic
    • claude-code
    • claude-code-skill
    • evals

    githubcrescita misurataApri fonte ↗

    13stelle GitHubstabile
  11. 11

    MCP
    Attivo

    Query Spanlens LLM observability from Cursor, Claude Desktop, or Continue via MCP.

    ↓ 32 download/settimanaTypeScriptLicenza: MIT

      mcpcrescita misurataApri fonte ↗

      Installa claude mcp add mcp-server -- npx @spanlens/mcp-server

      12stelle GitHubstabile
    • 12

      Agente
      Attivo

      Provide clear documentation for AgentStack’s MCP protocol, plugins, and ecosystem API with usage examples and tool references.

      • a2a
      • anthropic
      • claude-code
      • crewai
      • deep-learning

      githubcrescita misurataApri fonte ↗

      0stelle GitHubstabile
    • 13

      Agente
      Attivo

      MemroOS / memroos: memory OS and governance layer for AI agents, agent workflows, dispatch, proof, and context continuity.

      TypeScript
      • a2a
      • agent-governance
      • agent-memory
      • agent-orchestration
      • agent-workflows

      githubcrescita misurataApri fonte ↗

      7stelle GitHubstabile
    • 14

      Skill
      Dormiente

      A self-improving harness router for Claude Code.

      PythonLicenza: MIT
      • a-b-testing
      • ai-agent
      • ai-orchestration
      • ai-routing
      • ai-workflow

      githubcrescita misurataApri fonte ↗

      Installa /plugin marketplace add SeongwoongCho/adaptive-harness

      8stelle GitHubstabile
    • 15

      Skill
      Attivo

      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

      githubcrescita misurataApri fonte ↗

      Installa git clone https://github.com/peva3/anchor ~/.claude/skills/anchor

      8stelle GitHubstabile
    • 16

      Skill
      Attivo

      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

      githubcrescita misurataApri fonte ↗

      Installa /plugin marketplace add CoriChui/bakeoff

      10stelle GitHubstabile
    • 17

      Altro
      Attivo

      A Go-native framework for LLM agents, with OpenTelemetry observability built in.

      GoLicenza: Apache-2.0
      • a2a
      • agents
      • ai
      • anthropic
      • bedrock

      githubcrescita misurataApri fonte ↗

      10stelle GitHubstabile
    • 18

      MCP
      Attivo

      Architecture-first Python scaffold for an auditable multi-agent corporate credit desk using A2A, MCP, deterministic credit policies, model routing, and OpenTelemetry.

      Python
      • a2a-protocol
      • agentic-ai
      • auditability
      • clean-architecture
      • credit-risk

      githubcrescita misurataApri fonte ↗

      0stelle GitHubstabile
    • 19

      Agente
      Dormiente

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

      PythonLicenza: MIT
      • a2a
      • agents
      • contracts
      • evaluation
      • llm

      githubcrescita misurataApri fonte ↗

      0stelle GitHubstabile
    • 20

      Skill
      Attivo

      Marketing Mix Model expert agent plugin for Claude Code - pymc-marketing v0.18.2+

      Python
      • claude-code-agent
      • claude-code-plugin
      • claude-code-skill
      • data-analysis
      • data-analytics

      githubcrescita misurataApri fonte ↗

      Installa /plugin marketplace add Yakoub-ai/agent-mmm

      4stelle GitHubstabile
    • 21

      Agente
      Dormiente

      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

      githubcrescita misurataApri fonte ↗

      0stelle GitHubstabile
    • 22

      Agente
      Attivo

      A2A green-agent orchestrator for evaluating agents on the AppWorld benchmark, built on the AgentBeats SDK

      Python
      • a2a-protocol
      • agentbeats
      • appworld
      • evaluation
      • llm-agents

      githubcrescita misurataApri fonte ↗

      0stelle GitHubstabile
    • 23

      Skill
      Attivo

      🟪 Open-source runtime that ships any LangGraph or Google ADK agent as a production-ready FastAPI service. Bundled , AG-UI copilotkit API, chat UI, 15+ guardrails, MCP, OpenTelemetry, OIDC. One pip install. Self-hosted, no vendor lock-in.

      PythonLicenza: GPL-3.0
      • a2a-protocol
      • ag-ui-protocol
      • agent-platform
      • agentic-ai
      • agents

      githubcrescita misurataApri fonte ↗

      Installa git clone https://github.com/Idun-Group/idun-agent-platform ~/.claude/skills/idun-agent-platform

      199stelle GitHubstabile
    • 24

      Agente
      Dormiente

      AgentOps: Multi-agent infrastructure remediation platform. A2A protocol, agent coordination, HITL approval, auto-rollback.

      PythonLicenza: MIT
      • a2a-protocol
      • ai
      • automation
      • infrastructure
      • llm

      githubcrescita misurataApri fonte ↗

      0stelle GitHubstabile
    • 25

      Altro
      Attivo

      🔑 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

      githubcrescita misurataApri fonte ↗

      0stelle GitHubstabile