deepcode-cli — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by lessweb · Agent Tool · ★ 2.3k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is deepcode-cli safe to install? View the security audit →

About deepcode-cli

Deep Code CLI [![][npm-release-shield]][npm-release-link] [![][npm-downloads-shield]][npm-downloads-link] [![][github-contributors-shield]][github-contributors-link] [![][github-forks-shield]][github-forks-link] [![][github-stars-shield]][github-stars-link] [![][github-issues-shield]][github-issues-link] [![][github-issues-pr-shield]][github-issues-pr-link] [![][github-license-shield]][github-license-link] English · 中文 Deep Code 是专为 模型优化的终端 AI 编码助手,支持深度思考、推理强度控制、Agent Skills 以及 MCP 集成。 安装 在任意项目目录下运行 即可启动。 配置 创建 文件,内容如下: 配置文件与 Deep Code VSCode 插件 共享,无需重复配置。 完整配置说明(多层级优先级、环境变量等)请参阅 docs/configuration.md。 主要功能 Skills Deep Code CLI 支持 agent skills,允许您扩展助手的能力: Skills 会按以下优先级扫描:

ai-agentdeepseek

Quick Facts

Stars2,254
Forks217
LanguageTypeScript
CategoryAgent Tool
LicenseMIT
Quality Score64.9068810788052/100
Open Issues139
Last Updated2026-09-17
Created2026-04-28
Platformscli, node
Est. Tokens~15k

Compatible Skills

These tools work well together with deepcode-cli for enhanced workflows:

  • dao-code — semantic(0.44)+complementary+same_lang+similar_pop+shared_platform (66%)
  • deepseek-mcp-server — semantic(0.34)+complementary+same_lang+similar_pop+shared_platform (62%)
  • sandbase-harness — semantic(0.33)+complementary+same_lang+similar_pop+shared_platform (61%)
  • carboncode — semantic(0.56)+complementary+same_lang+shared_platform (60%)

deepcode-cli alternative? Top 6 similar tools

Looking for a deepcode-cli alternative? If you're comparing deepcode-cli with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • ouroboros by Q00 · ⭐ 6.1k

    Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budget

  • Overture by SixHq · ⭐ 641

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • Awesome-MCP-ZH by yzfly · ⭐ 7.7k

    MCP 资源精选, MCP指南,Claude MCP,MCP Servers, MCP Clients

  • codecompanion.nvim by olimorris · ⭐ 6.9k

    ✨ AI Coding, Vim Style

  • deepchat by ThinkInAIXYZ · ⭐ 6.3k

    🐬DeepChat - A smart assistant that connects powerful AI to your personal world

  • UltraRAG by OpenBMB · ⭐ 5.7k

    A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is deepcode-cli?

deepcode-cli is Deep Code 是专为 deepseek-v4 模型优化的终端 AI 编码助手,支持深度思考、推理强度控制以及 Agent Skills。. It is categorized as a Agent Tool with 2.3k GitHub stars.

What programming language is deepcode-cli written in?

deepcode-cli is primarily written in TypeScript. It covers topics such as ai-agent, deepseek.

How do I install or use deepcode-cli?

You can find installation instructions and usage details in the deepcode-cli GitHub repository at github.com/lessweb/deepcode-cli. The project has 2.3k stars and 217 forks, indicating an active community.

What license does deepcode-cli use?

deepcode-cli is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to deepcode-cli?

The top alternatives to deepcode-cli on Agent Skills Hub include ouroboros, Overture, Awesome-MCP-ZH. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools