Is the Micro-Agent MCP server actively maintained?

The Micro-Agent MCP server was last committed 1mo ago and has 8 contributors. Issue health: 20% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

Micro-Agent MCP Server

Name: fdueblab/Micro-Agent
Rating: 3.5 (1 reviews)
Author: fdueblab

fdueblab/Micro-Agent

Score: 62.6 Rank #5600 Agent Framework

[![AgentRank](https://agentrank-ai.com/api/v1/badge/fdueblab--Micro-Agent)](https://agentrank-ai.com/tool/fdueblab--Micro-Agent/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

Are you the maintainer of fdueblab/Micro-Agent? Claim this listing →

A lightweight AI agent framework for vertical domain applications | 面向垂域应用的轻量级 AI Agent 框架

Add AgentRank to Claude Code Discover and compare tools like fdueblab/Micro-Agent — your AI finds the right one automatically

Get API Access →

claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

fdueblab/Micro-Agent is a Python tool licensed under MIT. A lightweight AI agent framework for vertical domain applications | 面向垂域应用的轻量级 AI Agent 框架 Topics: ai-agent, fastapi, litellm, llm, mcp, rag, react-agent, vertical-domain.

Ranked #5600 out of 24846 indexed tools.

Ecosystem

Python MIT

ai-agentfastapilitellmllmmcpragreact-agentvertical-domain

Score Breakdown

Stars 15% 101

101 stars → growing community

Freshness 25% 1mo ago

Last commit 1mo ago → moderate activity

Issue Health 25% 20%

1/5 issues closed → many open issues

Contributors 10% 8

8 contributors → small team

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads N/A

Forks 18

Description Good

License MIT

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 42 days ago — a recent commit would boost your freshness score

Issue Health high impact

You have 4 open vs 1 closed issues — triaging stale issues improves health

Badge all embed codes →

Markdown

[![AgentRank](https://agentrank-ai.com/api/v1/badge/fdueblab--Micro-Agent)](https://agentrank-ai.com/tool/fdueblab--Micro-Agent/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

<a href="https://agentrank-ai.com/tool/fdueblab--Micro-Agent/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/fdueblab--Micro-Agent" alt="AgentRank"></a>

Embed Widget docs →

HTML

<script src="https://agentrank-ai.com/embed.js" data-tool="fdueblab/Micro-Agent"></script>

Details

Stars: 101
Forks: 18
Open Issues: 4
Closed Issues: 1
Contributors: 8
Dependents: —
Language: Python
License: MIT
Last Commit: 1mo ago

Matched Queries

topic:mcp

From the README

<div align="center">

<br>

**中文** | [English](README_en.md)

</div>

---

## 为什么选择 Micro-Agent

> 如果你需要为特定行业快速构建一个专业 Agent 并以 API 服务形式交付，Micro-Agent 是最短路径。

<div align="center">

| 能力 | Micro-Agent | LangGraph | AutoGen¹ | OpenClaw |
|:-----|:---:|:---:|:---:|:---:|
| 开箱即用 API 服务 | ✅ | ✅ | ❌ | ✅ |
| 垂域知识注入 (Skills) | ✅ | ❌ | ❌ | ✅ |
| 内置 RAG 检索增强 | ✅ | 生态 | 扩展 | ✅ |
| MCP 集成 | ✅ | ✅ | ✅ | ✅ |
| 流式 SSE 输出 | ✅ | ✅ | 需自建 | ✅ |
| 多 LLM Profile 配置 | ✅ | ❌ | ❌ | ❌ |
| 轻量（核心 <3K 行） | ✅ | ❌ | ❌ | ❌ |

</div>

> ¹ AutoGen 已进入维护模式，新项目建议使用 [Microsoft Agent Framework](https://github.com/microsoft/autogen)。

**各框架定位：** Micro-Agent 面向垂域专业 Agent 服务交付 · LangGraph 面向复杂多步工作流编排 · AutoGen 面向多角色智能体协作 · OpenClaw 面向个人自主 AI 助手

## 架构

<div align="center">

</div>

<br>

**核心组件：**

- **LLM Layer** — 通过 [litellm](https://github.com/BerriAI/litellm) 统一接口，一套代码切换 OpenAI / DeepSeek / Claude / Ollama 等任意模型
- **Agent Core** — ReAct 执行引擎（Think → Act → Observe 循环），支持 SubAgent 子任务分发与 REPL 沙箱执行
- **Memory** — 会话记忆系统，支持短

Read full README on GitHub →