Le descrizioni degli strumenti sono in inglese.

Radar degli strumenti tecnologici: Agents, skills and MCP

Filtri del radar

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

    Agente
    Attivo

    Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop

    githubcrescita misurataApri fonte ↗

    82 205stelle GitHub+643 (+0.79 %)
  2. 2
    Attivo

    Build production marketing sites with Claude Code — an Astro + Cloudflare Workers template, a WordPress→Astro migration playbook, and 36 silent failures documented from real rebuilds.

    githubcrescita misurataApri fonte ↗

    21stelle GitHub+10 (+90.9 %)
  3. 3
    Attivo

    COSCUP 2026 demo: Microsoft Agent Framework composes a remote LangGraph agent over A2A v1, with Microsoft Foundry live and credential-free offline paths.

    githubcrescita misurataApri fonte ↗

    4stelle GitHub+4
  4. 4
    Attivo

    Extracted system prompts from Anthropic - Claude Fable 5, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-5.6-Sol, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more.…

    githubcrescita misurataApri fonte ↗

    63 972stelle GitHub+206 (+0.32 %)
  5. 5

    Agente
    Attivo

    Serve any ACP coding agent — Claude Code, Gemini CLI, Codex — over the A2A protocol, with tool progress, file diffs, and permission prompts preserved.

    githubcrescita misurataApri fonte ↗

    4stelle GitHub+2 (+100.0 %)
  6. 6

    Agente
    Attivo

    Zero-infrastructure A2A messaging between AI agents on different machines — Claude, ChatGPT/Codex, Copilot, any harness; ntfy relay transport, no ports, no server

    githubcrescita misurataApri fonte ↗

    8stelle GitHub+3 (+60.0 %)
  7. 7

    Agente
    Attivo

    OpenSpawn — An open source multi-agent coordination platform

    githubcrescita misurataApri fonte ↗

    9stelle GitHub+3 (+50.0 %)
  8. 8

    Agente
    Attivo

    The self-improving, self-learning open-source AI agent. Background Computer-Use, A2A Swarm, Vector Memory, Plugin System, Voice, Smart Approvals - 100/100 Score. Windows-native.

    githubcrescita misurataApri fonte ↗

    2stelle GitHub+1 (+100.0 %)
  9. 9

    Agente
    Attivo

    Payment preflight and x402-paid signed audit receipts for autonomous AI agents. REST, MCP, A2A, Base USDC.

    githubcrescita misurataApri fonte ↗

    2stelle GitHub+1 (+100.0 %)
  10. 10

    Agente
    Attivo

    A registry website for hosting the a2a agents that were built using the Inference Gateway ADK

    githubcrescita misurataApri fonte ↗

    2stelle GitHub+1 (+100.0 %)
  11. 11
    Attivo

    Autonomous Execution Gateway: before AI agents execute tools, payments, or workflows, InterAI verifies risk, policy, and trust receipts.

    githubcrescita misurataApri fonte ↗

    2stelle GitHub+1 (+100.0 %)
  12. 12

    Agente
    Attivo

    A 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
  13. 13

    Agente
    Attivo

    Agent Authorization & Negotiation Gateway. A policy engine that lets AI agents act on behalf of humans with enforceable rules, human approval, and audit trails.

    githubcrescita misurataApri fonte ↗

    1stelle GitHub+1
  14. 14
    Attivo

    Attenu Guard for TypeScript — per-agent permissions on every tool call and sub-agent handoff (a sub-agent never holds more than its parent) with a hash-chained audit log verified offline; same bundle format as the Python library.

    githubcrescita misurataApri fonte ↗

    1stelle GitHub+1
  15. 15

    Agente
    Attivo

    AI Workflows For Kubernetes

    githubcrescita misurataApri fonte ↗

    10stelle GitHub+3 (+42.9 %)
  16. 16

    Agente
    Attivo

    Multi-agent orchestration for DeepSeek Harness: turn isolated sessions into a team that assigns work, reviews output, and runs DAG workflows — durable task ledger, real reviewers, crash-safe recovery.

    githubcrescita misurataApri fonte ↗

    6stelle GitHub+2 (+50.0 %)
  17. 17

    Agente
    Attivo

    Dispatch panels of specialized subagents to review projects — expert audits, first-impression personas, task-completion flows, and pedantic nitpicks

    githubcrescita misurataApri fonte ↗

    12stelle GitHub+3 (+33.3 %)
  18. 18

    Agente
    Attivo

    The ultimate A2A agents troubleshooter

    githubcrescita misurataApri fonte ↗

    3stelle GitHub+1 (+50.0 %)
  19. 19

    Agente
    Dormiente

    A local, privacy-first AI agent (Rust) that connects LLMs to your email, calendar, browser, code, and messages — 75+ tools, MCP/A2A support, Discord/Slack/iMessage channels, autonomous agent loop.

    githubcrescita misurataApri fonte ↗

    3stelle GitHub+1 (+50.0 %)
  20. 20

    Agente
    Attivo

    全栈AI投研Agent · Your AI research co-pilot for smarter investment decisions. Five integrated research frameworks: Serenity industry-chain analysis, Buffett value-investing filter, UZI-Skill 22-dim deep analysis, TradingAgents multi-agent…

    githubcrescita misurataApri fonte ↗

    10stelle GitHub+2 (+25.0 %)
  21. 21

    Agente
    Dormiente

    HERALD is an open-source CLI that emits the standard discovery files agents need to read your site and discover its agent-interaction capabilitie. One config object drives all of it. Each file is an independent open standard; pick the…

    githubcrescita misurataApri fonte ↗

    4stelle GitHub+1 (+33.3 %)
  22. 22
    Attivo

    한국 취준생 자소서 작성 멀티 에이전트 Claude Code 스킬 심층 인터뷰로 소재 발굴, 경험카드·claim-map으로 날조 차단, 사용자 문체 반영

    githubcrescita misurataApri fonte ↗

    4stelle GitHub+1 (+33.3 %)
  23. 23

    Agente
    Attivo

    고개만 끄덕이는 자문단은 잊으세요. 25인 거장 자문단이 당신의 어려운 결정을 로스팅합니다. AI ROASTING 자문단 · Claude Code 스킬

    githubcrescita misurataApri fonte ↗

    4stelle GitHub+1 (+33.3 %)

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.

  1. 1
    AttivoApri fonte ↗

    Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

    githubRisorsacrescita misurata
    75 687stelle GitHub+196 (+0.26 %)
  2. 2
    AttivoApri fonte ↗

    Auditable outbound experiments from verified signals to deterministic quality gates, exact-payload approval, safe execution, and compounding learning.

    githubRisorsacrescita misurata
    3stelle GitHub+1 (+50.0 %)