Die Werkzeugbeschreibungen sind auf Englisch.
Technologieradare: Agents, skills and MCP
Radarfilter
Werkzeug-Rangliste
Gemischte Rangfolge: Gemessenes Wachstum hat Vorrang. Rohwerte behalten ihr eigenes Zeitfenster; eine Änderung erfordert mindestens zwei Messungen in 7 Tagen.
- 1Aktiv
vcap-spec
AgentVCAP: Verified Commerce for Agent Protocols — Open standard for settling agent-to-agent transactions with cryptographic proof of delivery
githubgemessenes WachstumQuelle öffnen ↗
0GitHub-Sternestabil - 2Ruhend
Companion repo for Golden Jacket Field Notes Week 2: Reference implementations of Strands, AgentCore, MCP, and A2A.
githubgemessenes WachstumQuelle öffnen ↗
0GitHub-Sternestabil - 3Aktiv
pausemesh
AgentLets long-running AI workflows pause for approval and resume exactly once after disconnects or restarts, without binding to one agent protocol.
githubgemessenes WachstumQuelle öffnen ↗
0GitHub-Sternestabil - 4Aktiv
pollen
Agentpeer messaging between AI agents, with a human at the gate — one file, zero dependencies.
githubgeschätztes MomentumQuelle öffnen ↗
3GitHub-Sterne· - 5Aktiv
syntrueno
AgentZero-trust autonomous cloud-ops swarm on Google Cloud. Gemini agents diagnose live incidents, judge their own remediation plans, and execute real Cloud Run changes behind a single-use cryptographic human gate, then verify the change…
githubgeschätztes MomentumQuelle öffnen ↗
1GitHub-Sterne· - 6Aktiv
SMEAI
AgentAn agent marketplace for BNB Chain that calls every agent before it lists it
githubgeschätztes MomentumQuelle öffnen ↗
1GitHub-Sterne· - 7Aktiv
EU AI Act Article 12 compliant audit logger for A2A protocol agents
githubgeschätztes MomentumQuelle öffnen ↗
0GitHub-Sterne· - 8Aktiv
kyc-aml-multiagent
AgentMulti-agent KYC/AML prototype: MCP tool access with policy-based authorisation at the tool-call boundary, A2A handoff across Vertex AI and Bedrock, LangGraph workflow, audit trail
githubgeschätztes MomentumQuelle öffnen ↗
0GitHub-Sterne· - 9Aktiv
AI_Agent
AgentA powerful, multi-agent AI system demonstrating strict separation of concerns using Agent-to-Agent (A2A) communication and the Model Context Protocol (MCP) for complex web research and task execution.
githubgeschätztes MomentumQuelle öffnen ↗
0GitHub-Sterne· - 10Aktiv
An identity, authority, and lifecycle layer for always-on AI agents — reference model + runnable implementations. The existence layer beneath MCP and A2A.
githubgeschätztes MomentumQuelle öffnen ↗
0GitHub-Sterne· - 11Aktiv
agent-receipt-spec
AgentAgent Interaction Receipt (AIR) — verifiable, content-free receipts for machine-to-machine interactions. Spec + verifier + test vectors.
githubgeschätztes MomentumQuelle öffnen ↗
0GitHub-Sterne· - 12Ruhend
Audit of 100 AI agent projects' machine-readability to other AI agents. Average score: 6.3/100.
githubgeschätztes MomentumQuelle öffnen ↗
0GitHub-Sterne· - 13Ruhend
example-agents
AgentRepository for sample snippets of agents, covering a2a, langgraph, ollama setup, phoenix.
githubgeschätztes MomentumQuelle öffnen ↗
0GitHub-Sterne· - 140GitHub-Sterne·
- 15Aktiv
Manca
AgentThe missing trust layer for agent-to-agent commerce: a neutral clearinghouse where any agent buys AND sells, with machine-verifiable escrow, reputation, and day-one monetization.
githubgeschätztes MomentumQuelle öffnen ↗
0GitHub-Sterne· - 16Aktiv
kawal
AgentEvidence about ERC-8004 agents on BNB Smart Chain, gathered by calling them. Kawal dials the endpoint a registration declares, keeps every result, and writes the measurements back into the Reputation Registry. BNB Chain hackathon: The Smart…
githubgeschätztes MomentumQuelle öffnen ↗
0GitHub-Sterne· - 17Aktiv
Host-agent orchestration combining A2A agent-to-agent communication with MCP tool integration — registry, capability discovery, dynamic task routing
githubgeschätztes MomentumQuelle öffnen ↗
0GitHub-Sterne· - 18Ruhend
a2a-trace
AgentVisual debugger for Agent-to-Agent (A2A) multi-agent systems — real-time tracing of inter-agent communication
githubgeschätztes MomentumQuelle öffnen ↗
0GitHub-Sterne· - 19Aktiv
ops-agent-platform
AgentProduction-oriented AIOps agent engineering prototype with MCP, LangGraph, AG-UI, durable state, reliable tool execution, HITL, sandboxing, and evals.
githubgeschätztes MomentumQuelle öffnen ↗
0GitHub-Sterne· - 20Ruhend
Introduction to Agents, Agent Tools & Interoperability (MCP), Context Engineering: Sessions & Memory, Agent Quality, Prototype to Production
githubgeschätztes MomentumQuelle öffnen ↗
0GitHub-Sterne· - 21Ruhend
website
AgentOfficial website for AgentAnycast — decentralized P2P runtime for AI agents
githubgeschätztes MomentumQuelle öffnen ↗
0GitHub-Sterne· - 22Ruhend
agent-adoption-spec
AgentOpen specification for agent-readiness — 25 checks across HTTP-protocol and content-shape practices, organized into a 3-tier ladder (L1–L3). CC-BY 4.0.
githubgeschätztes MomentumQuelle öffnen ↗
0GitHub-Sterne·
Lern- und Referenzressourcen
Geschätzte Rangfolge: Für eine Messung sind zwei tägliche Werte nötig. Diese Ressourcen bleiben getrennt zugänglich und fließen nicht in die Hauptwertung ein.
- 1AktivQuelle öffnen ↗
learn-claude-code
AgentBash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
githubRessourcegeschätztes Momentum75 687GitHub-Sterne· - 2AktivQuelle öffnen ↗
agent-stack-builds
AgentA collection of projects built while learning the AI agent stack.
githubRessourcegeschätztes Momentum1GitHub-Sterne· - 3AktivQuelle öffnen ↗
ai-engineering-hub
AgentA collection of LLM-powered Real-World applications and projects
githubRessourcegeschätztes Momentum0GitHub-Sterne·