Google PageRank for AI agents. 25,000+ tools indexed.

Kun MCP Server

KunAgent/Kun

Score: 76.3 Rank #2687 Agent Framework
Are you the maintainer of KunAgent/Kun? Claim this listing →

Local-first AI agent workspace for coding, writing, design, research, and automation — one runtime for desktop GUI and TUI.

Add AgentRank to Claude Code Discover and compare tools like KunAgent/Kun — your AI finds the right one automatically
Get API Access →
claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

KunAgent/Kun is a TypeScript tool. Local-first AI agent workspace for coding, writing, design, research, and automation — one runtime for desktop GUI and TUI. Topics: agentic-workflow, ai-agent, ai-assistant, ai-design, automation, coding-agent, deepseek, desktop-app, electron, llm, local-first, mcp, multi-agent, openai-compatible, productivity, react, tui, typescript, writing-assistant.

Ranked #2687 out of 24840 indexed tools.

Has 6,321 GitHub stars.

Has 35 contributors.

Actively maintained with commits in the last week.

Ecosystem

TypeScript NOASSERTION
agentic-workflowai-agentai-assistantai-designautomationcoding-agentdeepseekdesktop-appelectronllmlocal-firstmcpmulti-agentopenai-compatibleproductivityreacttuitypescriptwriting-assistant

Score Breakdown

StarsFreshnessIssue HealthContributorsDependents
Stars 15% 6,321

6,321 stars → well-known project

Freshness 25% today

Last commit today → actively maintained

Issue Health 25% 99%

518/525 issues closed → responsive maintainer

Contributors 10% 35

35 contributors → active community

Dependents 25% 2

2 dependents → few downstream users

npm Downloads N/A
PyPI Downloads N/A
Forks 595
Description Good
License NOASSERTION

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

License low impact

Add an MIT or Apache-2.0 license to signal trust and enable adoption

Badge all embed codes →

AgentRank score for KunAgent/Kun
[![AgentRank](https://agentrank-ai.com/api/badge/tool/KunAgent--Kun)](https://agentrank-ai.com/tool/KunAgent--Kun/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/tool/KunAgent--Kun/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/badge/tool/KunAgent--Kun" alt="AgentRank"></a>

Embed Widget docs →

Embed a rich score widget on your site or blog.

<script src="https://agentrank-ai.com/embed.js" data-tool="KunAgent/Kun"></script>

Matched Queries

topic:mcp

From the README

<p align="center">
  
</p>

<h1 align="center">Kun — 本地优先的 AI Agent 工作台</h1>

<p align="center">
  让 AI 在真实项目中规划、执行、验证并交付。<br>
  桌面 GUI 与终端 TUI 共用同一个本地运行时,任务、审批、计划和证据始终连续。
</p>

<p align="center">
  <a href="https://github.com/KunAgent/Kun/releases">下载桌面版</a>
  &nbsp;·&nbsp;
  <a href="https://www.kun-agent.com/docs">阅读文档</a>
  &nbsp;·&nbsp;
  <a href="https://github.com/KunAgent/Kun">GitHub</a>
  &nbsp;·&nbsp;
  <a href="./README.en.md">English</a>
</p>

<p align="center">
  <a href="https://github.com/KunAgent/Kun/releases"></a>
  <a href="./LICENSE"></a>
  
  
</p>

<p align="center">
  
</p>

## Kun 是什么

Kun 是把 AI 从“回答问题”推进到“完成工作”的本地优先工作台。它以两个主模式组织真实工作:Code 面向软件交付,并在同一任务中提供 Design 画布;Work 面向写作、资料整理、文档分析和演示产出。Agent 可以读取工作区上下文、制定计划、调用工具、修改文件、运行验证,并把证据留在任务旁。

桌面 GUI 适合观察、审阅和控制过程;终端 TUI 适合专注于键盘工作。两者通过同一个本地 `kun serve` 运行时共享线程、目标、计划、审批和后台任务,而不是两套彼此割裂的会话。

## 一眼了解

| 你需要 | Kun 提供 |
| --- | --- |
| 构建、调试与发布软件 | Code 模式提供项目上下文、文件编辑、终端、Git / Worktree、Diff、测试和审查。 |
| 从需求走到可实现的设计 | 在同一 Code 任
Read full README on GitHub →

Get the weekly AgentRank digest

Top movers, new tools, ecosystem insights — straight to your inbox.