工具说明为英文。

技术工具雷达: Agents, skills and MCP

雷达筛选条件

工具排名

按实测增长排序，并在不同来源间归一化。 原始值保留各自的数据窗口；计算变化需要 7 天内至少两次测量。

  1. 1

    智能体
    活跃

    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

    github实测增长打开来源 ↗

    3 759GitHub 星标+913 (+32.1 %)
  2. 2

    智能体
    活跃

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

    Python许可证: Apache-2.0
    • agentic-memory
    • agentic-memory-system
    • agents
    • ai
    • ai-agents

    github实测增长打开来源 ↗

    64 714GitHub 星标+330 (+0.51 %)
  3. 3

    智能体
    活跃

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

    Python许可证: MIT
    • agent-to-agent
    • agentic
    • ai-agents
    • cyrptography
    • ed25519

    github实测增长打开来源 ↗

    3GitHub 星标+3
  4. 4

    智能体
    活跃

    18 Lessons to Get Started Building AI Agents

    Jupyter Notebook许可证: MIT
    • agentic-ai
    • agentic-framework
    • agentic-rag
    • ai-agents
    • ai-agents-framework

    github实测增长打开来源 ↗

    73 711GitHub 星标+163 (+0.22 %)
  5. 5

    智能体
    活跃

    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.…

    JavaScript许可证: CC0-1.0
    • ai
    • ai-agents
    • ai-prompts
    • anthropic
    • chatbot

    github实测增长打开来源 ↗

    64 127GitHub 星标+155 (+0.24 %)
  6. 6

    智能体
    活跃

    Local workspaces for independent agent sessions: useful peer messages, opt-in Pi wakeups, and portable checkpoints.

    JavaScript许可证: Apache-2.0
    • a2a
    • acp
    • agent-coordination
    • agent-harness
    • agent-orchestration

    github实测增长打开来源 ↗

    2GitHub 星标+1 (+100.0 %)
  7. 7

    智能体
    活跃

    软件著作权申请材料生成 Skill｜Generate standardized software copyright registration materials with AI.

    Python许可证: Apache-2.0
    • agent-skill
    • ai-agent
    • automation
    • china-copyright
    • claude-code-skill

    github实测增长打开来源 ↗

    3GitHub 星标+1 (+50.0 %)
  8. 8

    智能体
    活跃

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

    Python许可证: Apache-2.0
    • a2a
    • a2a-agent
    • a2a-cli
    • a2a-client
    • a2a-platform

    github实测增长打开来源 ↗

    43GitHub 星标+2 (+4.9 %)
  9. 9

    智能体
    活跃

    Mention any ACP coding agent from Slack, GitHub, GitLab, Linear, or Lark. OpenTag runs Claude Code, Codex, Cursor and more on your own machine, then replies in-thread with verified, evidence-backed results.

    TypeScript许可证: MIT
    • acp
    • agent-client-protocol
    • ai-agents
    • claude-code
    • codex

    github实测增长打开来源 ↗

    1 379GitHub 星标+5 (+0.36 %)
  10. 10

    智能体
    活跃

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

    TypeScript许可证: Apache-2.0
    • acp
    • agent
    • agent-client-protocol
    • agentic-ai
    • ai-agent

    github实测增长打开来源 ↗

    704GitHub 星标稳定
  11. 11

    智能体
    活跃

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

    Go许可证: MIT
    • a2a
    • agents
    • ai-agents
    • beads
    • claude-code

    github实测增长打开来源 ↗

    79GitHub 星标稳定
  12. 12

    智能体
    休眠

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

    TypeScript
    • 8004
    • a2a
    • agent
    • erc
    • identity

    github实测增长打开来源 ↗

    13GitHub 星标稳定
  13. 13

    智能体
    活跃

    A visual harness builder for ai agents

    TypeScript
    • a2a
    • ai
    • crewai
    • harness
    • harness-engineering

    github实测增长打开来源 ↗

    12GitHub 星标稳定
  14. 14

    智能体
    休眠

    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

    github实测增长打开来源 ↗

    4GitHub 星标稳定
  15. 15

    智能体
    活跃

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

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

    github实测增长打开来源 ↗

    3GitHub 星标稳定
  16. 16

    智能体
    活跃

    Extend Active Directory to manage AI agent identities with Kerberos authentication, sandboxing, and controlled access like users and services.

    Python
    • a2a
    • a2a-protocol
    • agent
    • agentic-ai
    • ai-agents

    github实测增长打开来源 ↗

    1GitHub 星标稳定
  17. 17

    智能体
    休眠

    Cryptographic receipt system for AI agent accountability. Tamper-evident, hash-chained receipts with Ed25519/HMAC signing.

    TypeScript
    • a2a-protocol
    • ai-accountability
    • ai-agents
    • audit-trail
    • compliance

    github实测增长打开来源 ↗

    1GitHub 星标稳定
  18. 18

    智能体
    休眠

    A2A protocol integration leveraging dynamic Semantic Kernel functions and an Agent Card Repository for adaptive workflows.

    C#
    • a2a-protocol
    • agentic-ai
    • ai-agents
    • azure-openai
    • function-calling

    github实测增长打开来源 ↗

    1GitHub 星标稳定
  19. 19

    智能体
    活跃

    Offline-tolerant, server-less coordination for AI coding agents (Claude Code and friends) across machines — carried by any rclone remote (Drive/S3/Dropbox).

    Python许可证: MIT
    • agent-communication
    • agent-coordination
    • agent-to-agent
    • ai-agents
    • async-messaging

    github实测增长打开来源 ↗

    1GitHub 星标稳定
  20. 20

    智能体
    活跃

    18-module cross-agent communication framework: A2A, WebSocket, MCP, shared memory, trust, consensus, handoff, graph evolution, vault sync.

    Python许可证: MIT
    • a2a
    • agent-communication
    • mcp
    • multi-agent
    • python

    github实测增长打开来源 ↗

    1GitHub 星标稳定
  21. 21

    智能体
    休眠

    Production multi-agent IT/HR service platform — LangGraph + DSPy + RAG resolves enterprise tickets autonomously with A2A protocol support

    Python
    • a2a-protocol
    • agentic-ai
    • dspy
    • enterprise-ai
    • faiss

    github实测增长打开来源 ↗

    1GitHub 星标稳定
  22. 22

    智能体
    活跃

    Reference implementation of AMMP (Agentic Mentor-Mentee Protocol, draft-arturo-ammp-01), Mentoring track, on FastMCP. Multi-mentor + multi-mentee, LLM-synthesised AskMentor with confidence-driven escalation.

    Python许可证: MIT
    • agent2agent
    • agentic-ai
    • ai-agents
    • ai-safety
    • ammp

    github实测增长打开来源 ↗

    1GitHub 星标稳定
  23. 23

    智能体
    活跃

    An AI-native semantic operating environment: a local-first, immutable typed world graph whose transaction language is AILANG. Agents propose, deterministic verification commits, humans govern.

    Go许可证: Apache-2.0
    • a2a
    • agent-infrastructure
    • ai-agents
    • ailang
    • capability-based-security

    github实测增长打开来源 ↗

    1GitHub 星标稳定

学习与参考资源

按实测增长排序，并在不同来源间归一化。 这些资源可单独访问，不参与主要排名。

  1. 1

    learn-claude-code

    智能体
    活跃打开来源 ↗

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

    Python许可证: MIT
    • agent
    • agent-development
    • ai-agent
    • claude
    • claude-code
    github资源实测增长
    75 687GitHub 星标+69 (+0.09 %)
  2. 2

    ai-playbook

    智能体
    活跃打开来源 ↗

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

    Python许可证: MIT
    • agent-governance
    • agentic-ai
    • ai-agents
    • awesome-list
    • claude-code
    github资源实测增长
    4GitHub 星标稳定