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

MiniAgent MCP Server

ZhuLinsen/MiniAgent

Score: 59.9 Rank #6317 MCP Server
[![AgentRank](https://agentrank-ai.com/api/v1/badge/ZhuLinsen--MiniAgent)](https://agentrank-ai.com/tool/ZhuLinsen--MiniAgent/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
Are you the maintainer of ZhuLinsen/MiniAgent? Claim this listing →

A tiny, plugin-first Python Agent Harness. Multi-LLM, MCP, Skills, and resumable sessions.

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

Overview

ZhuLinsen/MiniAgent is a Python tool licensed under Apache-2.0. A tiny, plugin-first Python Agent Harness. Multi-LLM, MCP, Skills, and resumable sessions. Topics: agent, llm, llms, mcp, claude, claudecode, manus, openai.

Ranked #6317 out of 24846 indexed tools.

Ecosystem

Python Apache-2.0
agentllmllmsmcpclaudeclaudecodemanusopenai

Score Breakdown

StarsFreshnessIssue HealthContributorsDependents
Stars 15% 212

212 stars → growing community

Freshness 25% 1mo ago

Last commit 1mo ago → moderate activity

Issue Health 25% 13%

1/8 issues closed → many open issues

Contributors 10% 2

2 contributors → solo project

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A
PyPI Downloads N/A
Forks 45
Description Good
License Apache-2.0

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

Freshness high impact

Last commit was 31 days ago — a recent commit would boost your freshness score

Issue Health high impact

You have 7 open vs 1 closed issues — triaging stale issues improves health

Badge all embed codes →

AgentRank score for ZhuLinsen/MiniAgent
[![AgentRank](https://agentrank-ai.com/api/v1/badge/ZhuLinsen--MiniAgent)](https://agentrank-ai.com/tool/ZhuLinsen--MiniAgent/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/tool/ZhuLinsen--MiniAgent/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/ZhuLinsen--MiniAgent" 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="ZhuLinsen/MiniAgent"></script>

Matched Queries

topic:mcp

From the README

# MiniAgent

🚀 **5分钟手搓一个 AI Coding 助手 + 命令行版 Manus!** | [English](README_EN.md)

<div align="center">
  

  
  
  
</div>

## 💡 核心特性

**一个 `agent.py` 核心文件,复刻 Claude Code 的编程能力 + Manus 的系统操控能力!**

MiniAgent 是一个**极简、透明、强大的 CLI Agent 框架**,拒绝臃肿的依赖和复杂的架构:

- 🧠 **Code Agent**: 像 Claude Code 一样写代码、修 Bug、跑测试
- 🦾 **OS Agent**: 像 Manus 一样操控浏览器、编辑文档、管理应用
- ⚡ **极简实现**: 核心引擎 `agent.py` 完全透明可控,适合学习和魔改
- 🤖 **全模型支持**: DeepSeek、OpenAI、Gemini、Claude 等所有兼容 OpenAI 接口的模型
- 🔌 **高扩展性**: 极简装饰器模式,3行代码即可挂载自定义工具
- 🔄 **双模式工具调用**: 文本解析模式(透明可学习)+ 原生 Function Calling 模式(更可靠)
- 🎯 **Skill 系统**: 可复用的 Agent 配置,内置 coder/researcher/reviewer/tester 四个角色
- 🛡️ **安全防护**: 危险命令自动拦截确认,防止 LLM 幻觉导致破坏性操作
- 💬 **流式输出**: 打字机效果实时输出,长对话自动压缩上下文
- 🔗 **MCP 协议**: 支持连接 MCP 工具服务器,接入社区生态
- 🤝 **Agent 编排**: 内置编排器,支持任务分解 + 多角色协同

## 🤔 Why MiniAgent?

| | MiniAgent | smolagents | pydantic-ai | LangChain |
|---|---|---|---|---|
| **核心定位** | CLI Agent 教科书 | HuggingFace 生态 | 企业级类型安全 | 万能框架 |
| **核心代码** | 单文件可读 | ~1,000行 | 182MB | 10万+行 |
Read full README on GitHub →

Get the weekly AgentRank digest

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