Die Werkzeugbeschreibungen sind auf Englisch.

Technologieradare: Agents, skills and MCP

Radarfilter

Werkzeug-Rangliste

Nach gemessenem Wachstum und quellenübergreifend normalisiert sortiert. Rohwerte behalten ihr eigenes Zeitfenster; eine Änderung erfordert mindestens zwei Messungen in 7 Tagen.

  1. 1

    Agent
    Aktiv

    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…

    githubgemessenes WachstumQuelle öffnen ↗

    156GitHub-Sterne+19 (+13.9 %)
  2. 2

    Agent
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    4GitHub-Sterne+2 (+100.0 %)
  3. 3

    Agent
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    8GitHub-Sterne+3 (+60.0 %)
  4. 4

    Agent
    Aktiv

    OpenSpawn — An open source multi-agent coordination platform

    githubgemessenes WachstumQuelle öffnen ↗

    9GitHub-Sterne+3 (+50.0 %)
  5. 5

    Agent
    Aktiv

    AI Workflows For Kubernetes

    githubgemessenes WachstumQuelle öffnen ↗

    10GitHub-Sterne+3 (+42.9 %)
  6. 6
    Aktiv

    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.

    githubgemessenes WachstumQuelle öffnen ↗

    6GitHub-Sterne+2 (+50.0 %)
  7. 7

    Agent
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    12GitHub-Sterne+3 (+33.3 %)
  8. 8

    Agent
    Aktiv

    The ultimate A2A agents troubleshooter

    githubgemessenes WachstumQuelle öffnen ↗

    3GitHub-Sterne+1 (+50.0 %)
  9. 9

    Agent
    Ruhend

    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.

    githubgemessenes WachstumQuelle öffnen ↗

    3GitHub-Sterne+1 (+50.0 %)
  10. 10

    Agent
    Aktiv

    Open-source cybersecurity analysis agent for Claude Code. Scans projects for vulnerabilities across all OWASP 2025 Top 10 and CWE Top 25 categories. 11 security domains, 60+ secret patterns, parallel subagent analysis, professional report…

    githubgemessenes WachstumQuelle öffnen ↗

    257GitHub-Sterne+12 (+4.9 %)
  11. 11

    Agent
    Aktiv

    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…

    githubgemessenes WachstumQuelle öffnen ↗

    10GitHub-Sterne+2 (+25.0 %)
  12. 12

    Agent
    Ruhend

    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…

    githubgemessenes WachstumQuelle öffnen ↗

    4GitHub-Sterne+1 (+33.3 %)
  13. 13

    Agent
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    4GitHub-Sterne+1 (+33.3 %)
  14. 14
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    4GitHub-Sterne+1 (+33.3 %)
  15. 15
    Aktiv

    小红书/抖音/快手/视频号/B站 自媒体账号体检+爆款拆解工具。扫同赛道找对标、拆爆款为什么爆、诊断为什么没人看,顺手出可粘贴仿写初稿。支持带货电商模式。支持codex, claude code, workbuddy

    githubgemessenes WachstumQuelle öffnen ↗

    217GitHub-Sterne+9 (+4.3 %)
  16. 16
    Ruhend

    This project demonstrates Agent-to-Agent (A2A) conversations using LangGraph with the A2A protocol. It includes implementations in both **Python** and **TypeSc…

    githubgemessenes WachstumQuelle öffnen ↗

    14GitHub-Sterne+2 (+16.7 %)
  17. 17
    Aktiv

    Amazon Bedrock AgentCore enterprise platform accelerator with AWS CDK, Terraform organization guardrails, MCP/A2A agents, security, memory, and observability.

    githubgemessenes WachstumQuelle öffnen ↗

    5GitHub-Sterne+1 (+25.0 %)
  18. 18
    Aktiv

    Reference architecture for secure multi-agent delegation chains using Cedar-based permission attenuation on Amazon Bedrock AgentCore. Demonstrates scope narrowing, tamper-proof token chains, and audit logging across A2A agent interactions.

    githubgemessenes WachstumQuelle öffnen ↗

    5GitHub-Sterne+1 (+25.0 %)
  19. 19

    Agent
    Aktiv

    Mac App to use Codex Micro or Creator Micro with Claude, Hermes, and more harnesses. Full customization of lights and actions right in your Menu Bar.

    githubgemessenes WachstumQuelle öffnen ↗

    5GitHub-Sterne+1 (+25.0 %)
  20. 20
    Aktiv

    Mandatory final sanity check before commits/PRs - catches security vulnerabilities, logic errors, and bugs that slip through tests

    githubgemessenes WachstumQuelle öffnen ↗

    5GitHub-Sterne+1 (+25.0 %)
  21. 21

    Agent
    Aktiv

    Autonomous text-to-game pipeline for Godot, powered by Claude Code,Codex,Opencode

    githubgemessenes WachstumQuelle öffnen ↗

    529GitHub-Sterne+11 (+2.1 %)
  22. 22
    Aktiv

    SHM v6.10.1 — 自演化超图记忆 (CudaAccel: 本机 embedding 强制 CUDA)

    githubgemessenes WachstumQuelle öffnen ↗

    6GitHub-Sterne+1 (+20.0 %)

Lern- und Referenzressourcen

Nach gemessenem Wachstum und quellenübergreifend normalisiert sortiert. Diese Ressourcen bleiben getrennt zugänglich und fließen nicht in die Hauptwertung ein.

  1. 1
    AktivQuelle öffnen ↗

    Learn to build AI agents with Strands framework. Covers LLM integration via Amazon Bedrock/Anthropic, AWS service connections, tool implementation with MCP/A2A protocols, and agent evaluation using LangFuse/RAGAS.

    githubRessourcegemessenes Wachstum
    166GitHub-Sterne+60 (+56.6 %)
  2. 2
    AktivQuelle öffnen ↗

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

    githubRessourcegemessenes Wachstum
    3GitHub-Sterne+1 (+50.0 %)
  3. 3
    AktivQuelle öffnen ↗

    A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

    githubRessourcegemessenes Wachstum
    208GitHub-Sterne+10 (+5.1 %)