DeepSeek-Reasonix — security grade SAFE, quality 74/100

Security audit verdict: SAFE · quality 74/100

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 esengine · Agent Tool · ★ 35.7k

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

🔒 Is DeepSeek-Reasonix safe to install? View the security audit →

About DeepSeek-Reasonix

English &nbsp;·&nbsp; 简体中文 &nbsp;·&nbsp; Website &nbsp;·&nbsp; Guide &nbsp;·&nbsp; Architecture &nbsp;·&nbsp; Benchmarks <a

agentagent-frameworkai-agentai-codingclicoding-agentdeepseekdeveloper-toolsinkllm

Quick Facts

Stars35,735
Forks2,439
LanguageTypeScript
CategoryAgent Tool
LicenseMIT
Quality Score73.5311907720481/100
Open Issues325
Last Updated2026-10-03
Created2026-04-21
Platformscli, node
Est. Tokens~1501k

Compatible Skills

These tools work well together with DeepSeek-Reasonix for enhanced workflows:

  • deepseek-mcp-server — semantic(0.26)+complementary+rare_topics+same_lang+similar_pop+shared_platform (59%)
  • oh-my-pi — semantic(0.38)+complementary+same_lang+similar_pop+shared_platform (58%)
  • prompt-caching — semantic(0.21)+complementary+rare_topics+same_lang+similar_pop+shared_platform (57%)
  • tokenjuice — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)
  • agent-kanban — semantic(0.16)+complementary+same_lang+similar_pop+shared_platform (56%)

DeepSeek-Reasonix alternative? Top 6 similar tools

Looking for a DeepSeek-Reasonix alternative? If you're comparing DeepSeek-Reasonix 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.

  • oh-my-pi by can1357 · ⭐ 34.2k

    ⌥ Coding agent with the IDE wired in. Built by Stencil Labs.

  • superset by superset-sh · ⭐ 14.8k

    Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscrip

  • rtk by rtk-ai · ⭐ 82.3k

    CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero depend

  • repomix by yamadashy · ⭐ 28.7k

    📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for w

  • plandex by plandex-ai · ⭐ 15.6k

    Open source AI coding agent. Designed for large projects and real world tasks.

  • dify by langgenius · ⭐ 157.8k

    Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. De

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is DeepSeek-Reasonix?

DeepSeek-Reasonix is DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.. It is categorized as a Agent Tool with 35.7k GitHub stars.

What programming language is DeepSeek-Reasonix written in?

DeepSeek-Reasonix is primarily written in TypeScript. It covers topics such as agent, agent-framework, ai-agent.

How do I install or use DeepSeek-Reasonix?

You can find installation instructions and usage details in the DeepSeek-Reasonix GitHub repository at github.com/esengine/DeepSeek-Reasonix. The project has 35.7k stars and 2439 forks, indicating an active community.

What license does DeepSeek-Reasonix use?

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

What are the best alternatives to DeepSeek-Reasonix?

The top alternatives to DeepSeek-Reasonix on Agent Skills Hub include oh-my-pi, superset, rtk. 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