CodeBoarding/CodeBoarding

Health v2 · maintenance only

Adoption not part of the score

2400 stars · 199 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

CodeBoarding is an open-source CLI and toolchain that combines static analysis with LLM reasoning to generate interactive architecture diagrams and component-level documentation for codebases. Results can be explored in a browser webview, a VS Code extension, or a GitHub Action for architecture-aware PR diffs.

Use cases

• generate architecture diagrams from a codebase
• understand a large unfamiliar repository quickly
• review AI agent-generated changes with system context
• onboard new developers with visual codebase maps
• add architecture-aware diffs to pull requests in CI
• document component structure of a repo automatically

When to choose

• you need visual architecture maps of Python, TypeScript, Go, Java, Rust, PHP, or C# repos
• you want to keep humans and AI coding agents aligned on system structure
• you prefer local analysis with your own LLM provider (OpenAI, Anthropic, Ollama, etc.)

When to avoid

• you need runtime profiling or dynamic call-graph tracing rather than static analysis
• you want fully offline diagram generation without any LLM provider
• you need a general-purpose UML modeling tool rather than generated codebase maps

Facets

cli-tool · maturity active

static-site-generator documentation data-visualization llm-inference agent-framework developer-tools developer-tools documentation data-visualization large-language-models python cli cross-platform browser editor-plugin static-analysis architecture-diagrams code-visualization lsp diagrams-as-code code-onboarding mermaid vscode-extension github-action explainability ai-agents

Member repositories

For agents

markdown · JSON · MCP: product_card(name="CodeBoarding/CodeBoarding")