Agents, skills and MCP radar: agents and agent frameworks

Momentum based on available 7-day snapshots for Agents, skills and MCP: measured with two snapshots, estimated otherwise. Each value shows its own source window. This page reads stored snapshots only.

Radar filters

Tool ranking

Ranked by measured growth, normalized across sources. Raw values keep their source-specific window, shown under each tool; a change requires at least two snapshots from the last 7 days.

  1. 1
    Active

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

    githubmeasured growthOpen source ↗

    3 848GitHub stars+820 (+27.1 %)
  2. 2

    Agent
    Active

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

    githubmeasured growthOpen source ↗

    3 678GitHub stars+229 (+6.6 %)
  3. 3
    Active

    18 Lessons to Get Started Building AI Agents

    githubmeasured growthOpen source ↗

    73 711GitHub stars+163 (+0.22 %)
  4. 4
    Active

    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.…

    githubmeasured growthOpen source ↗

    64 127GitHub stars+155 (+0.24 %)
  5. 5
    Active

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

    githubmeasured growthOpen source ↗

    1GitHub stars+1
  6. 6

    Agent
    Active

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

    githubmeasured growthOpen source ↗

    43GitHub stars+2 (+4.9 %)
  7. 7
    Active

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

    githubmeasured growthOpen source ↗

    687GitHub stars+5 (+0.73 %)
  8. 8

    Agent
    Active

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

    githubmeasured growthOpen source ↗

    704GitHub starsstable
  9. 9

    Agent
    Active

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

    githubmeasured growthOpen source ↗

    79GitHub starsstable
  10. 10
    Dormant

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

    githubmeasured growthOpen source ↗

    13GitHub starsstable
  11. 11
    Active

    A visual harness builder for ai agents

    githubmeasured growthOpen source ↗

    12GitHub starsstable
  12. 12

    Agent
    Dormant

    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.

    githubmeasured growthOpen source ↗

    4GitHub starsstable
  13. 13

    Agent
    Active

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

    githubmeasured growthOpen source ↗

    3GitHub starsstable
  14. 14

    Agent
    Active

    Durable, authenticated, and optionally federated routing for A2A Protocol agents.

    githubmeasured growthOpen source ↗

    1GitHub starsstable
  15. 15

    Agent
    Active

    The seat between a caller and an agent provider: the agent stays where its owner runs it, funduq makes it reachable over standard AG-UI and A2A, holds each run, and records who asked and through whose hands the work passed. Mechanism and…

    githubmeasured growthOpen source ↗

    1GitHub starsstable
  16. 16

    Agent
    Dormant

    Falsification Chain of Thought — post-hoc verification of AI judgments using falsificationism to counter sycophancy bias

    githubmeasured growthOpen source ↗

    1GitHub starsstable
  17. 17
    Active

    A Claude Code skill that runs code-changing tasks with reviewed plans, controlled multi-agent edits, and evidence-backed verification — no review theater.

    githubmeasured growthOpen source ↗

    1GitHub starsstable
  18. 18

    Agent
    Active

    Multi-agent coordination via versioned letters — as a Claude Code skill

    githubmeasured growthOpen source ↗

    1GitHub starsstable
  19. 19
    Dormant

    Shopify store auditor for Claude Code - 6-dimension audit: catalog, navigation, SEO, app stack, CRO signals. Works MCP-connected or public.

    githubmeasured growthOpen source ↗

    1GitHub starsstable
  20. 20

    Agent
    Dormant

    🚢 AI 项目出海前的 Launch QA 船坞:README、浏览器、趋势雷达和发布检查一站验船。

    githubmeasured growthOpen source ↗

    1GitHub starsstable
  21. 21

    Agent
    Active

    Structured, multi-agent development pipeline

    githubmeasured growthOpen source ↗

    1GitHub starsstable
  22. 22

    Agent
    Active

    Where humans find AI talent — A2A-compliant agent registry and discovery

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  23. 23

    Agent
    Dormant

    A2A + MCP bridge : internal bot-to-bot calls, external agent discovery, and secure Streamable HTTP tools.

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  24. 24
    Active

    Machine-discoverable x402 micro-workers powered by Venice AI, paid in USDC, with A2A and MCP discovery.

    githubmeasured growthOpen source ↗

    0GitHub starsstable

Learning resources

Ranked by measured growth, normalized across sources. These resources remain available separately and do not take part in the main tool ranking.

  1. 1
    ActiveOpen source ↗

    Learn it. Build it. Ship it for others.

    githubResourcemeasured growth
    52 415GitHub stars+1 070 (+2.1 %)