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

codeAgent MCP Server

Harvil1/codeAgent

Score: 66.5 Rank #4777 MCP Server
[![AgentRank](https://agentrank-ai.com/api/v1/badge/Harvil1--codeAgent)](https://agentrank-ai.com/tool/Harvil1--codeAgent/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
Are you the maintainer of Harvil1/codeAgent? Claim this listing →

CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the task is done — all with a transparent, extensible tool loop.

Add AgentRank to Claude Code Discover and compare tools like Harvil1/codeAgent — your AI finds the right one automatically
Get API Access →
claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

Harvil1/codeAgent is a Python tool licensed under MIT. CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the task is done — all with a transparent, extensible tool loop. Topics: agent, ai-agent, cli, coding-agent, context-engineering, deepseek, llm, mcp, python, terminal.

Ranked #4777 out of 24846 indexed tools.

Ecosystem

Python MIT
agentai-agentclicoding-agentcontext-engineeringdeepseekllmmcppythonterminal

Score Breakdown

StarsFreshnessIssue HealthContributorsDependents
Stars 15% 332

332 stars → growing community

Freshness 25% 8d ago

Last commit 8d ago → recently updated

Issue Health 25% 50%

No issues filed → no history to score

Contributors 10% 1

1 contributor → solo project

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A
PyPI Downloads N/A
Forks 40
Description Detailed
License MIT

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

How to Improve

Contributors medium impact

Single-contributor projects carry bus-factor risk — welcoming contributors boosts confidence

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

AgentRank score for Harvil1/codeAgent
[![AgentRank](https://agentrank-ai.com/api/v1/badge/Harvil1--codeAgent)](https://agentrank-ai.com/tool/Harvil1--codeAgent/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/tool/Harvil1--codeAgent/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/Harvil1--codeAgent" 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="Harvil1/codeAgent"></script>

Matched Queries

topic:mcp

From the README

# CodeAgent

> 自学习 AI Agent 命令行工具——交互体验对标 claude code,Windows 优先,开箱即用。

[English](./README.en.md) | 简体中文

CodeAgent 是一个跑在终端里的 AI 编程助手:你用自然语言下指令,它读代码、改文件、跑命令、查资料,把活干完。它有自己的一套「长本事」机制——从对话轨迹里沉淀可复用的技能,越用越顺手。

## 🧭 这是一份手写的「中文版 claude code」

不是套壳,也不是翻译——是从交互界面到 Agent 主循环一行行手写出来的完整实现,**注释全是中文**:

- 📚 **想学 Agent 开发?这就是活教材。** 工具自注册、上下文分级压缩、权限审批、子代理团队、工作流引擎、记忆系统——一个真实可跑的 Agent 全链路都在这儿,每个模块都是「大白话流程 → 参数 → 返回」的保姆级中文注释,读代码像读教程。
- 🛠 **欢迎上手改。** 觉得哪里不顺手?fork 了直接改——代码结构清晰、注释到位,改起来不费劲。欢迎 PR:修 bug、加功能、优化界面都行。
- 💬 **有问题社区问。** 卡住了、看不懂了、想讨论设计,直接去 [Issues](https://github.com/Harvil1/codeAgent/issues) 或 [Discussions](https://github.com/Harvil1/codeAgent/discussions) 发帖,有问必答。

## ✨ 特性

**终端体验(对标 claude code)**
- 流式回答圆角框、思考流暗色框、工具事件行(`● Bash(...)` + `⎿ 结果`)
- 危险命令 / 白名单外写文件的**审批面板**:允许一次 / 总是允许 / 拒绝三选,面板答完自擦不污染上下文
- Ctrl+C 语义分明:回合中一键中断、双击强退;审批面板上 Ctrl+C 一击取消并中断整轮
- 皮肤系统、页脚状态栏、命令补全、输入历史、粘贴大段文本自动落盘引用

**模型与工具**
- 多模型接入:OpenAI 兼容协议(默认 DeepSeek)与 Anthropic 协议均可配;主模型 + 辅助小模型(压缩/检索/记忆提取等杂活走便宜模型)
- 工具自注册体系:`tools/
Read full README on GitHub →

Get the weekly AgentRank digest

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