agentica MCP Server
shibing624/agentica
[](https://agentrank-ai.com/tool/shibing624--agentica/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) One person, a team of agents. Multi-session CLI that collaborates across terminals; /goal keeps long tasks running; WeChat/WeCom/Feishu gateway lets you call them back when you walk away. Async Python SDK, persistent memory, self-evolving skills.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
shibing624/agentica is a Python tool licensed under Apache-2.0. One person, a team of agents. Multi-session CLI that collaborates across terminals; /goal keeps long tasks running; WeChat/WeCom/Feishu gateway lets you call them back when you walk away. Async Python SDK, persistent memory, self-evolving skills. Topics: agent, agents, langchain, llm, multi-agent, agentica, agent-framework, ai-agent, cli, mcp, rag, self-evolving, workflow.
Ranked #568 out of 24846 indexed tools.
In the top 3% of all indexed tools.
Actively maintained with commits in the last week.
Ecosystem
Score Breakdown
353 stars → growing community
Last commit 5d ago → actively maintained
21/22 issues closed → responsive maintainer
8 contributors → small team
No dependents → no downstream usage
252 weekly installs → early adoption
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Badge all embed codes →
[](https://agentrank-ai.com/tool/shibing624--agentica/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/shibing624--agentica/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/shibing624--agentica" alt="AgentRank"></a> Matched Queries
From the README
<p align="center">
<a href="https://github.com/shibing624/agentica">
</a>
</p>
<h1 align="center">Agentica</h1>
<p align="center"><b>一个人，一支 agent 团队。</b><br />CLI 终端、本机 Web、Desktop App 是同一套产品，跑在你自己的机器上。</p>
<h3 align="center"><a href="#桌面版">⬇️ Download Desktop App</a></h3>
<p align="center">macOS · Windows · Linux</p>
<p align="center">
<a href="https://badge.fury.io/py/agentica"></a>
<a href="https://github.com/shibing624/agentica"></a>
<a href="https://github.com/shibing624/agentica/blob/main/LICENSE"></a>
<a href="https://github.com/shibing624/agentica/blob/main/requirements.txt"></a>
<a href="#社区与支持"></a>
</p>
<p align="center">简体中文 | <a href="https://github.com/shibing624/agentica/blob/main/README_EN.md">English</a></p>
## 为什么选 Agentica
### 1. 🏆 同一个模型，更准、更快、更省钱
工具面刻意收窄、接口保持底层，对 DeepSeek 等开放模型深度适配。和 OpenAI Codex 各跑同一个模型、同一批公开题目，正面对比：
<p align="center">
</p>
**编程题全对、数据分析题准确率更高——而且快一倍、输入 token 少三分之二。** 复现命令、逐项指标与原始 `predictions.jsonl` 见 [评测页](https:/ Read full README on GitHub → Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.