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 652GitHub stars+1 125 (+44.5 %)
  2. 2

    Agent
    Active

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

    githubmeasured growthOpen source ↗

    3 615GitHub stars+256 (+7.6 %)
  3. 3

    Agent
    Active

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

    githubmeasured growthOpen source ↗

    64 675GitHub stars+396 (+0.62 %)
  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+361 (+0.57 %)
  5. 5
    Active

    18 Lessons to Get Started Building AI Agents

    githubmeasured growthOpen source ↗

    73 711GitHub stars+286 (+0.39 %)
  6. 6

    Agent
    Active

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

    githubmeasured growthOpen source ↗

    82 205GitHub stars+277 (+0.34 %)
  7. 7
    Active

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

    githubmeasured growthOpen source ↗

    4GitHub stars+4
  8. 8
    Active

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

    githubmeasured growthOpen source ↗

    3GitHub stars+3
  9. 9

    Agent
    Active

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

    githubmeasured growthOpen source ↗

    4GitHub stars+2 (+100.0 %)
  10. 10

    Agent
    Active

    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.

    githubmeasured growthOpen source ↗

    3GitHub stars+2 (+200.0 %)
  11. 11

    Agent
    Active

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

    githubmeasured growthOpen source ↗

    8GitHub stars+3 (+60.0 %)
  12. 12

    Agent
    Active

    OpenSpawn — An open source multi-agent coordination platform

    githubmeasured growthOpen source ↗

    9GitHub stars+3 (+50.0 %)
  13. 13

    Agent
    Active

    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

    githubmeasured growthOpen source ↗

    2GitHub stars+1 (+100.0 %)
  14. 14

    Agent
    Active

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

    githubmeasured growthOpen source ↗

    2GitHub stars+1 (+100.0 %)
  15. 15
    Active

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

    githubmeasured growthOpen source ↗

    2GitHub stars+1 (+100.0 %)
  16. 16

    Agent
    Dormant

    Vendor-neutral identity verification for AI agents

    githubmeasured growthOpen source ↗

    2GitHub stars+1 (+100.0 %)
  17. 17
    Active

    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.

    githubmeasured growthOpen source ↗

    1GitHub stars+1
  18. 18

    Agent
    Active

    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…

    githubmeasured growthOpen source ↗

    11GitHub stars+3 (+37.5 %)
  19. 19
    Active

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

    githubmeasured growthOpen source ↗

    6GitHub stars+2 (+50.0 %)
  20. 20

    Agent
    Active

    AI Workflows For Kubernetes

    githubmeasured growthOpen source ↗

    12GitHub stars+3 (+33.3 %)
  21. 21

    Agent
    Active

    The ultimate A2A agents troubleshooter

    githubmeasured growthOpen source ↗

    3GitHub stars+1 (+50.0 %)
  22. 22

    Agent
    Dormant

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

    githubmeasured growthOpen source ↗

    3GitHub stars+1 (+50.0 %)
  23. 23

    Agent
    Dormant

    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.

    githubmeasured growthOpen source ↗

    3GitHub stars+1 (+50.0 %)

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 ↗

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

    githubResourcemeasured growth
    75 687GitHub stars+126 (+0.17 %)
  2. 2
    ActiveOpen source ↗

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

    githubResourcemeasured growth
    3GitHub stars+1 (+50.0 %)