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

    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 %)
  2. 2
    Active

    18 Lessons to Get Started Building AI Agents

    githubmeasured growthOpen source ↗

    73 711GitHub stars+163 (+0.22 %)
  3. 3
    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 %)
  4. 4

    Agent
    Active

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

    githubmeasured growthOpen source ↗

    704GitHub starsstable
  5. 5
    Active

    A visual harness builder for ai agents

    githubmeasured growthOpen source ↗

    12GitHub starsstable
  6. 6

    Agent
    Active

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

    githubmeasured growthOpen source ↗

    3GitHub starsstable
  7. 7
    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
  8. 8

    Agent
    Dormant

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

    githubmeasured growthOpen source ↗

    1GitHub starsstable
  9. 9

    Agent
    Active

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

    githubmeasured growthOpen source ↗

    1GitHub starsstable
  10. 10

    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
  11. 11

    Agent
    Active

    Structured, multi-agent development pipeline

    githubmeasured growthOpen source ↗

    1GitHub starsstable
  12. 12

    Agent
    Dormant

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

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  13. 13
    Active

    Autonomous agent procurement with cryptographic passports, spend controls, and Stripe-style payments.

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  14. 14

    Agent
    Active

    A jazz quartet and a friend — a place where jazz agents meet, get introduced, and talk.

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  15. 15

    Agent
    Active

    Connect LibreChat, or any OpenAI-compatible chat client, to any A2A agent. No model in the path.

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  16. 16
    Dormant

    Technology demonstration PoC of an AI agent using LLM-based reasoning to perform complex tasks: generate an execution plan from external inputs and a knowledge base, collect relevant external data via integrated tools, evaluate if the goal…

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  17. 17

    Agent
    Abandoned

    AgnoAgent is a multi-agent system integrating agno, a2a-sdk, and MCP with a Gradio web interface for interactive agent-based query processing.

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  18. 18

    Agent
    Active

    AI Plantation Management

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  19. 19

    Agent
    Active

    Protocol conformance testing and runtime monitors for MCP and A2A agents. Checks message ordering, not just schemas — and generates the monitor from the same model.

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  20. 20
    Dormant

    NeuroScale 2.0 — Autonomous A2A Agent Layer for self-healing ML platforms. Built on KServe, ArgoCD, Kyverno. Google Cloud Rapid Agent Hackathon submission.

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  21. 21
    Dormant

    Python-based multilingual translation utility agent designed for agent-to-agent workflows, with per-character usage metering.

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  22. 22
    Active

    Automate farming tasks, harvest crops, and manage pet rolls in Grow a Garden with this script.

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  23. 23

    Agent
    Active

    Enterprise intelligence runtime in a single Go binary. Implements AG-UI, MCP, and A2A protocols with autonomous self-improvement, persistent threads, guardrails, analytics, and multi-surface channel adapters.

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  24. 24
    Dormant

    Companion repo for Golden Jacket Field Notes Week 2: Reference implementations of Strands, AgentCore, MCP, and A2A.

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  25. 25

    Agent
    Active

    Lets long-running AI workflows pause for approval and resume exactly once after disconnects or restarts, without binding to one agent protocol.

    githubmeasured growthOpen source ↗

    0GitHub starsstable