DeepSeek-Code-Whale MCP工具 是 AI Skill Hub 本期精选AI工具之一。综合评分 8.0 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
专为DeepSeek模型优化的终端AI编码助手。支持MCP协议、技能扩展、提示词缓存优化等功能。适合需要高效代码生成和编程辅助的开发者,特别是DeepSeek用户。
DeepSeek-Code-Whale MCP工具 是一款基于 Go 开发的开源工具,专注于 DeepSeek、MCP、编码助手 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
专为DeepSeek模型优化的终端AI编码助手。支持MCP协议、技能扩展、提示词缓存优化等功能。适合需要高效代码生成和编程辅助的开发者,特别是DeepSeek用户。
DeepSeek-Code-Whale MCP工具 是一款基于 Go 开发的开源工具,专注于 DeepSeek、MCP、编码助手 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 方式一:go install(推荐) go install github.com/usewhale/DeepSeek-Code-Whale@latest # 方式二:从源码编译 git clone https://github.com/usewhale/DeepSeek-Code-Whale cd DeepSeek-Code-Whale go build -o deepseek-code-whale . # 方式三:下载预编译二进制 # 访问 Releases 页面下载对应平台二进制文件 # https://github.com/usewhale/DeepSeek-Code-Whale/releases
# 查看帮助 deepseek-code-whale --help # 基本运行 deepseek-code-whale [options] <input> # 详细使用说明请查阅文档 # https://github.com/usewhale/DeepSeek-Code-Whale
# deepseek-code-whale 配置说明 # 查看配置选项 deepseek-code-whale --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export DEEPSEEK_CODE_WHALE_CONFIG="/path/to/config.yml"
<p align="center"> <img src="docs/logo.svg" alt="Whale — AI coding agent for DeepSeek, in any environment" width="640"> </p>
<p align="center"> <a href="./README.zh.md">简体中文</a> · <strong>English</strong> </p>
<p align="center"> <a href="https://github.com/usewhale/Whale/releases"><img src="https://img.shields.io/github/v/release/usewhale/Whale?label=release" alt="release"></a> <a href="https://www.npmjs.com/package/@usewhale/whale"><img src="https://img.shields.io/npm/v/@usewhale/whale" alt="npm"></a> <a href="https://github.com/usewhale/Whale/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/usewhale/Whale/ci.yml?label=CI" alt="CI"></a> <a href="./LICENSE"><img src="https://img.shields.io/github/license/usewhale/Whale" alt="license"></a> <a href="https://github.com/usewhale/Whale/stargazers"><img src="https://img.shields.io/github/stars/usewhale/Whale?style=flat&logo=github&label=stars" alt="GitHub stars"></a> <img src="https://img.shields.io/badge/prompt%20cache-98%25-brightgreen" alt="98% prompt cache hit"> </p>
<p align="center"> Blazingly fast · ~98% prompt cache hit · Zero bloat </p>
<p align="center"> <b>Whale — AI coding agent for DeepSeek, in any environment.</b><br> Long context, tools, and programmable workflows —<br> start in the terminal, scale to desktop and beyond. </p>
---
Any platform:
npm install -g @usewhale/whale
macOS:
brew install usewhale/tap/whale
Linux:
curl -fsSL https://raw.githubusercontent.com/usewhale/Whale/main/scripts/install.sh | sh
Windows PowerShell:
Requires Windows 10 or Windows Server 2016 or later.
irm https://raw.githubusercontent.com/usewhale/Whale/main/scripts/install.ps1 | iex
Windows CMD:
powershell -NoProfile -ExecutionPolicy Bypass -Command "irm https://raw.githubusercontent.com/usewhale/Whale/main/scripts/install.ps1 | iex"
```bash
whale setup
Whale's Dynamic Workflows let you script multi-agent orchestration in JavaScript:
// .whale/workflows/research.js
const results = await parallel([
() => agent("Search for best practices in Go error handling"),
() => agent("Find common Go error handling mistakes"),
]);
return agent("Synthesize both findings into a concise guide");
Fan-out research · Multi-perspective review · Pipeline processing · Adversarial validation
✅ Claude Code compatible — workflow scripts written for Claude Code work as-is in Whale.
⚠️ Disabled by default — run/configin the TUI and enableDynamic workflows, or add[workflows] enabled = trueto.whale/config.local.toml.
Learn more: Workflow Overview · Custom Workflow Guide
---
| Extension | What it does | Get started |
|---|---|---|
| **MCP Servers** | Connect to 1,000+ tools (databases, APIs, browser automation) | [docs/mcp.en.md](docs/mcp.en.md) |
| **Skills** | Load domain expertise — code review, git-worktree, and more | [docs/skills.en.md](docs/skills.en.md) |
| **Subagents** | Define focused child-agent roles such as reviewers or researchers | [docs/agents.en.md](docs/agents.en.md) |
| **Plugins** | Extend Whale's runtime with custom logic | [docs/plugins.en.md](docs/plugins.en.md) |
| **Hooks** | Run scripts on lifecycle events | [docs/hooks.en.md](docs/hooks.en.md) |
---
专业的DeepSeek编码代理,技术栈扎实,MCP支持完整。社区维护活跃,代码质量高,值得深度开发者使用。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
经综合评估,DeepSeek-Code-Whale MCP工具 在AI工具赛道中表现稳健,质量优秀。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | DeepSeek-Code-Whale |
| 原始描述 | 开源MCP工具:Whale 是专为 DeepSeek 模型优化的终端 AI 编码助手,支持 MCP, Skills, 缓存优化。。⭐136 · Go |
| Topics | DeepSeekMCP编码助手CLI工具Go开发 |
| GitHub | https://github.com/usewhale/DeepSeek-Code-Whale |
| License | MIT |
| 语言 | Go |
收录时间:2026-05-17 · 更新时间:2026-05-19 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。