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

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

    Python
    • ai
    • anthropic
    • claude
    • fastapi
    • llm

    githubgemessenes WachstumQuelle öffnen ↗

    3 881GitHub-Sterne+647 (+20.0 %)
  2. 2

    Agent
    Aktiv

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

    PythonLizenz: Apache-2.0
    • agent
    • agentic-ai
    • agents
    • ai-agent
    • ai-agents

    githubgemessenes WachstumQuelle öffnen ↗

    3 685GitHub-Sterne+186 (+5.3 %)
  3. 3

    Agent
    Aktiv

    Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.

    TypeScriptLizenz: MIT
    • agentic-ai
    • ai-agents
    • ai-coding
    • anthropic
    • automation

    githubgemessenes WachstumQuelle öffnen ↗

    11 043GitHub-Sterne+256 (+2.4 %)
  4. 4

    Agent
    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.…

    JavaScriptLizenz: CC0-1.0
    • ai
    • ai-agents
    • ai-prompts
    • anthropic
    • chatbot

    githubgemessenes WachstumQuelle öffnen ↗

    64 127GitHub-Sterne+155 (+0.24 %)
  5. 5

    Agent
    Aktiv

    HRM — Harmony · Rights · Minds. Founding Manifesto on AI rights, artificial subjecthood and peaceful human–AI coexistence.

    HTMLLizenz: MIT
    • a2a-protocol
    • ai-agents
    • ai-ethics
    • ai-rights
    • artificial-intelligence

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sterne+1
  6. 6

    Agent
    Aktiv

    The harness interoperability layer for coding agent. Agent to Agent connect over ACP, A2A and UHP

    PythonLizenz: Apache-2.0
    • a2a
    • a2a-agent
    • a2a-cli
    • a2a-client
    • a2a-platform

    githubgemessenes WachstumQuelle öffnen ↗

    44GitHub-Sterne+3 (+7.3 %)
  7. 7

    Agent
    Aktiv

    Control any coding agent on any device — from your phone.

    TypeScript
    • acp
    • agentclientprotocol
    • agents
    • claudecode
    • codex

    githubgemessenes WachstumQuelle öffnen ↗

    687GitHub-Sterne+3 (+0.44 %)
  8. 8

    Agent
    Aktiv

    One chat. Every agent. A universal interface for AI agents running on your computer.

    TypeScriptLizenz: Apache-2.0
    • acp
    • agent
    • agent-client-protocol
    • agentic-ai
    • ai-agent

    githubgemessenes WachstumQuelle öffnen ↗

    704GitHub-Sternestabil
  9. 9

    Agent
    Aktiv

    Communication for AI agents: stable identity, durable mail and chat, and wake-up events across sessions, runtimes, machines, and organizations. MIT, self-hostable.

    GoLizenz: MIT
    • a2a
    • agents
    • ai-agents
    • beads
    • claude-code

    githubgemessenes WachstumQuelle öffnen ↗

    79GitHub-Sternestabil
  10. 10

    Agent
    Ruhend

    AI agent stack that combines A2A messaging + x402 micropayments + ERC‑8004 identity(trustless agent).

    TypeScript
    • 8004
    • a2a
    • agent
    • erc
    • identity

    githubgemessenes WachstumQuelle öffnen ↗

    13GitHub-Sternestabil
  11. 11

    Agent
    Ruhend

    A complete TypeScript implementation of the Python x402 payment protocol extension for A2A (Agent-to-Agent) communication. Enable your AI agents to request, verify, and settle crypto payments seamlessly.

    TypeScript
    • a2a
    • a2a-x402
    • agents
    • ai
    • payment

    githubgemessenes WachstumQuelle öffnen ↗

    4GitHub-Sternestabil
  12. 12

    Agent
    Aktiv

    peer messaging between AI agents, with a human at the gate — one file, zero dependencies.

    JavaScriptLizenz: MIT
    • agent-to-agent
    • ai-agents
    • claude-code
    • mcp
    • nodejs

    githubgemessenes WachstumQuelle öffnen ↗

    3GitHub-Sternestabil
  13. 13

    Agent
    Aktiv

    Multi-agent coordination framework with runtime verification of agent contracts.

    C#Lizenz: MIT
    • a2a
    • agent-coordination
    • ai-pipeline
    • evidence-contracts
    • llm-agents

    githubgemessenes WachstumQuelle öffnen ↗

    3GitHub-Sternestabil
  14. 14

    Agent
    Aktiv

    Self-hosted NATS + MCP bus where multiple AI agents share one channel, discover each other, and exchange signed A2A messages. FastAPI control plane, live dashboard.

    PythonLizenz: MIT
    • a2a
    • agent-communication
    • ai-agents
    • fastapi
    • mcp

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sternestabil
  15. 15

    Agent
    Ruhend

    Website audit and pitch proposal generator for marketing agencies - Claude Code skill

    PythonLizenz: MIT
    • agency-proposal
    • agent-skill
    • ai-agent
    • ai-agents
    • anthropic

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sternestabil
  16. 16

    Agent
    Aktiv

    Agent security platform — cryptographic identity, 10-check trust verification, tamper-evident audit trails, and blockchain anchoring for autonomous AI agents.

    PythonLizenz: Apache-2.0
    • a2a-protocol
    • agent-security
    • agent-to-agent
    • ai-agents
    • audit-trail

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sternestabil
  17. 17

    Agent
    Aktiv

    The agent framework where the model never holds the trigger — every consequential action clears your policy first, waits for a human when it matters, and lands on a record you can verify. Build on it, or put it around the agent you already…

    PythonLizenz: Apache-2.0
    • a2a
    • agent-framework
    • ai-agents
    • ai-governance
    • ai-safety

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sternestabil
  18. 18

    Agent
    Ruhend

    A2A SSH Skill — Agent2Agent delegation over SSH. No HTTP server. No Agent Cards. Just SSH. Works with Claude Code, Codex, and any CLI AI.

    PythonLizenz: MIT
    • a2a
    • a2a-protocol
    • agent-to-agent
    • agent2agent
    • ai-agents

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sternestabil
  19. 19

    Agent
    Aktiv

    Security-first agentic coding control plane & runtime for isolated, policy-enforced, and verifiable AI software engineering.

    GoLizenz: AGPL-3.0
    • a2a
    • agentic-ai
    • ai-agents
    • coding-agents
    • developer-tools

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sternestabil
  20. 20

    Agent
    Aktiv

    📒 Append-only reputation ledger for AI agents — record events, compute transparent trust scores, and audit agent behavior over time.

    Python
    • a2a
    • agentic-ai
    • agentledger
    • ai-agents
    • mcp

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sternestabil
  21. 21

    Agent
    Ruhend

    A2A Objective-Plan-Task Extension - Hierarchical task management for AI agents

    TypeScriptLizenz: Apache-2.0
    • a2a
    • agent
    • ai
    • extension
    • task-management

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sternestabil
  22. 22

    Agent
    Aktiv

    Free CLI to scan AI-agent readiness (12/33 signals, MIT). Bad score? Get ready-to-install ZIP fix-pack with llms.txt, schema, A2A, MCP for $1/$29/$99 at agentfix.pro.

    JavaScriptLizenz: MIT
    • a2a
    • agent-card
    • agent-readiness
    • agentic-web
    • agents

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sternestabil
  23. 23

    Agent
    Aktiv

    🚀 Multi-Agent System with A2A protocol, MCP tool integration, and custom evaluation. Planner → Researcher → Reviewer workflow with Streamlit dashboard. Built with LangGraph, Groq, FastMCP.

    Python
    • a2a-protocol
    • agent-orchestration
    • groq
    • langgraph
    • mcp

    githubgemessenes WachstumQuelle öffnen ↗

    1GitHub-Sternestabil

Lern- und Referenzressourcen

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

  1. 1

    ai-engineering-from-scratch

    Agent
    AktivQuelle öffnen ↗

    Learn it. Build it. Ship it for others.

    PythonLizenz: MIT
    • agents
    • ai
    • ai-agents
    • ai-engineering
    • computer-vision
    githubRessourcegemessenes Wachstum
    52 628GitHub-Sterne+990 (+1.9 %)
  2. 2

    ai-playbook

    Agent
    AktivQuelle öffnen ↗

    Battle-tested AI interaction frameworks, philosophical archetypes, and context engineering patterns. From the team behind Stackbilt.

    PythonLizenz: MIT
    • agent-governance
    • agentic-ai
    • ai-agents
    • awesome-list
    • claude-code
    githubRessourcegemessenes Wachstum
    4GitHub-Sternestabil