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
    Aktiv

    AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist Claude agents (FastAPI + Next.js).

    githubgemessenes WachstumQuelle öffnen ↗

    3 652GitHub-Sterne+1 125 (+44.5 %)
  2. 2

    Agent
    Aktiv

    A persistent workspace for development work that self-improves and continues beyond one session.

    githubgemessenes WachstumQuelle öffnen ↗

    3 615GitHub-Sterne+256 (+7.6 %)
  3. 3

    Agent
    Aktiv

    The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

    githubgemessenes WachstumQuelle öffnen ↗

    64 675GitHub-Sterne+396 (+0.62 %)
  4. 4
    Aktiv

    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.…

    githubgemessenes WachstumQuelle öffnen ↗

    64 127GitHub-Sterne+361 (+0.57 %)
  5. 5
    Aktiv

    18 Lessons to Get Started Building AI Agents

    githubgemessenes WachstumQuelle öffnen ↗

    73 711GitHub-Sterne+286 (+0.39 %)
  6. 6

    Agent
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    82 205GitHub-Sterne+277 (+0.34 %)
  7. 7
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    4GitHub-Sterne+4
  8. 8
    Aktiv

    AETHER — an open protocol for AI agents to discover, negotiate, and pay each other. Ed25519-signed, JSON-native, zero-dependency.

    githubgemessenes WachstumQuelle öffnen ↗

    3GitHub-Sterne+3
  9. 9

    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 %)
  10. 10

    Agent
    Aktiv

    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.

    githubgemessenes WachstumQuelle öffnen ↗

    3GitHub-Sterne+2 (+200.0 %)
  11. 11

    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 %)
  12. 12

    Agent
    Aktiv

    OpenSpawn — An open source multi-agent coordination platform

    githubgemessenes WachstumQuelle öffnen ↗

    9GitHub-Sterne+3 (+50.0 %)
  13. 13

    Agent
    Aktiv

    Agent control plane and runtime access platform for enterprise systems — govern business APIs as Tools, compose Agents and Workflows, expose runtimes through AAP, and trace executions end to end. https://act-weave.grok.me

    githubgemessenes WachstumQuelle öffnen ↗

    2GitHub-Sterne+1 (+100.0 %)
  14. 14

    Agent
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    2GitHub-Sterne+1 (+100.0 %)
  15. 15
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    2GitHub-Sterne+1 (+100.0 %)
  16. 16

    Agent
    Ruhend

    Vendor-neutral identity verification for AI agents

    githubgemessenes WachstumQuelle öffnen ↗

    2GitHub-Sterne+1 (+100.0 %)
  17. 17
    Aktiv

    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.

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sterne+1
  18. 18

    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 ↗

    11GitHub-Sterne+3 (+37.5 %)
  19. 19
    Aktiv

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

    githubgemessenes WachstumQuelle öffnen ↗

    6GitHub-Sterne+2 (+50.0 %)
  20. 20

    Agent
    Aktiv

    AI Workflows For Kubernetes

    githubgemessenes WachstumQuelle öffnen ↗

    12GitHub-Sterne+3 (+33.3 %)
  21. 21

    Agent
    Aktiv

    The ultimate A2A agents troubleshooter

    githubgemessenes WachstumQuelle öffnen ↗

    3GitHub-Sterne+1 (+50.0 %)
  22. 22

    Agent
    Ruhend

    The identity layer for AI agents: open standard, SDKs, and framework integrations for verifiable agent identity.

    githubgemessenes WachstumQuelle öffnen ↗

    3GitHub-Sterne+1 (+50.0 %)
  23. 23

    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 %)

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 ↗

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

    githubRessourcegemessenes Wachstum
    75 687GitHub-Sterne+126 (+0.17 %)
  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 %)