Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.
Sentrux is a static analysis MCP server written in pure Rust that gives AI coding agents continuous, quantified feedback on codebase architecture as they work. The core workflow runs in a scan-score-improve loop: the tool analyzes a project using tree-sitter plugins covering 52 languages, assigns a numeric quality score, and exposes that data to agents so they can target specific structural problems and re-scan after changes. It ships three complementary interfaces: a live interactive treemap GUI for visual exploration of project structure, a `sentrux check` command for CI rule enforcement with clean exit codes, and a `sentrux gate` command that saves a quality baseline before an agent session and then compares against it afterward to catch degradation. The MCP server integrates directly with Claude Code via its plugin marketplace, and with Cursor, Windsurf, and other MCP clients through a standard JSON config block. Developers using AI agents to build or maintain codebases are the primary audience, particularly those who have noticed code quality quietly deteriorating across long agentic sessions.
- ✓Open-source license (MIT)
- ✓Recently active
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
git clone https://github.com/sentrux/sentrux && cp sentrux/*.md ~/.claude/agents/1 items in this repository
Scan a project with sentrux to get structural health grades (A-F) across 14 dimensions including coupling, cycles, cohesion, dead code, and test coverage. Use when the user wants to check code quality, architecture health, or before/after an agent session.
Subagents overview
What people ask about sentrux
What is sentrux/sentrux?
+
sentrux/sentrux is subagents for the Claude AI ecosystem. Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust. It has 2.5k GitHub stars and was last updated 2mo ago.
How do I install sentrux?
+
You can install sentrux by cloning the repository (https://github.com/sentrux/sentrux) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is sentrux/sentrux safe to use?
+
Our security agent has analyzed sentrux/sentrux and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains sentrux/sentrux?
+
sentrux/sentrux is maintained by sentrux. The last recorded GitHub activity is from 2mo ago, with 26 open issues.
Are there alternatives to sentrux?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy sentrux to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/sentrux-sentrux)<a href="https://claudewave.com/repo/sentrux-sentrux"><img src="https://claudewave.com/api/badge/sentrux-sentrux" alt="Featured on ClaudeWave: sentrux/sentrux" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Production-ready platform for agentic workflow development.
The agent engineering platform.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.