Codeboarding – Interactive architecture diagrams for codebases

CodeBoarding has launched an open-source tool that generates interactive architecture diagrams for codebases by combining static analysis with LLM reasoning. The tool produces layered diagrams, component-level documentation, and Mermaid output that can be embedded in IDEs, CI pipelines, pull requests, and documentation. Developers can use the VS Code or Open VSX extension to visualize system architecture and review AI-generated changes before they introduce hidden technical debt.

See what your AI is building before it breaks. CodeBoarding gives developers and coding agents a visual map of a codebase. It combines static analysis with LLM reasoning to generate architecture diagrams, component-level documentation, and navigable outputs you can use in your IDE, CI, and docs. Website https://codeboarding.org · Open VSX extension https://open-vsx.org/extension/CodeBoarding/codeboarding · Explore examples https://codeboarding.org/diagrams · VS Code extension https://marketplace.visualstudio.com/items?itemName=Codeboarding.codeboarding · GitHub Action https://github.com/marketplace/actions/codeboarding-diagram-first-documentation · Discord https://discord.gg/T5zHTJYFuy Install the extension from Open VSX. - Keep architecture visible while agents code. - Review AI-generated changes with system context before they turn into hidden debt. - Understand large repositories faster with layered diagrams and component breakdowns. - Share the same visual model across local workflows, IDEs, pull requests, and docs. - High-level system architecture diagrams. - Deeper component diagrams for important subsystems. - Markdown documentation in .codeboarding/ . - Mermaid output that is easy to embed in docs and PRs. - Incremental updates when only part of the codebase changes. graph LR Application Orchestrator Repository Manager "Application Orchestrator & Repository Manager" LLM Agent Core "LLM Agent Core" Static Code Analyzer "Static Code Analyzer" Agent Tooling Interface "Agent Tooling Interface" Incremental Analysis Engine "Incremental Analysis Engine" Documentation Diagram Generator "Documentation & Diagram Generator" Application Orchestrator Repository Manager -- "Orchestrator initiates analysis workflow, leveraging incremental updates based on detected code changes." -- Incremental Analysis Engine Application Orchestrator Repository Manager -- "Orchestrator passes project context and triggers the main analysis workflow for the LLM Agent." -- LLM Agent Core Incremental Analysis Engine -- "Incremental engine requests static analysis for specific code segments new or changed ." -- Static Code Analyzer Static Code Analyzer -- "Static analyzer provides analysis results to the incremental engine for caching." -- Incremental Analysis Engine LLM Agent Core -- "LLM Agent invokes specialized tools to interact with the codebase and analysis data." -- Agent Tooling Interface Agent Tooling Interface -- "Agent tools query the static analysis engine for detailed code insights." -- Static Code Analyzer Static Code Analyzer -- "Static analysis engine provides requested data to the agent tools." -- Agent Tooling Interface LLM Agent Core -- "LLM Agent delivers structured analysis insights for documentation and diagram generation." -- Documentation Diagram Generator click Application Orchestrator Repository Manager href "https://github.com/CodeBoarding/CodeBoarding/blob/main/.codeboarding/Application Orchestrator Repository Manager.md" "Details" click LLM Agent Core href "https://github.com/CodeBoarding/CodeBoarding/blob/main/.codeboarding/LLM Agent Core.md" "Details" click Static Code Analyzer href "https://github.com/CodeBoarding/CodeBoarding/blob/main/.codeboarding/Static Code Analyzer.md" "Details" click Agent Tooling Interface href "https://github.com/CodeBoarding/CodeBoarding/blob/main/.codeboarding/Agent Tooling Interface.md" "Details" click Incremental Analysis Engine href "https://github.com/CodeBoarding/CodeBoarding/blob/main/.codeboarding/Incremental Analysis Engine.md" "Details" click Documentation Diagram Generator href "https://github.com/CodeBoarding/CodeBoarding/blob/main/.codeboarding/Documentation Diagram Generator.md" "Details" For a deeper architecture walkthrough, see .codeboarding/overview.md /CodeBoarding/CodeBoarding/blob/main/.codeboarding/overview.md . uv sync --frozen source .venv/bin/activate On Windows: .venv\Scripts\activate python install.py python main.py full --local /path/to/repo Requires Python 3.12 or 3.13 . The recommended install method is pipx https://pipx.pypa.io , which keeps the CLI in its own isolated environment: pipx install codeboarding --python python3.12 codeboarding-setup codeboarding full --local /path/to/repo Or, if you prefer pip, install into a virtual environment not the global Python : pip install codeboarding codeboarding-setup codeboarding full --local /path/to/repo Output is written to /path/to/repo/.codeboarding/ . python install.py and codeboarding-setup download language server binaries to ~/.codeboarding/servers/ , shared across projects. Node.js and its bundled npm is required for the Python, TypeScript, JavaScript, and PHP language servers; if neither node nor CODEBOARDING NODE PATH is set, setup downloads a pinned Node.js runtime into ~/.codeboarding/servers/nodeenv/ automatically. On first run, CodeBoarding creates ~/.codeboarding/config.toml . Set one provider there or use environment variables. provider openai api key = "sk-..." anthropic api key = "sk-ant-..." google api key = "AIza..." vercel api key = "vck ..." aws bearer token bedrock = "..." ollama base url = "http://localhost:11434" openrouter api key = "sk-..." llm agent model = "gemini-3-flash" parsing model = "gemini-3-flash" Shell environment variables such as OPENAI API KEY , ANTHROPIC API KEY , GOOGLE API KEY , and OLLAMA BASE URL take precedence over the config file. For private repositories, set GITHUB TOKEN in your environment. Analyze a local repository python main.py full --local ./my-project Increase diagram depth python main.py full --local ./my-project --depth-level 2 Re-analyze only changed parts when possible python main.py incremental --local ./my-project Update a single component by ID python main.py partial --local ./my-project --component-id "1.2" Analyze a remote GitHub repository python main.py full https://github.com/pytorch/pytorch CLI https://github.com/CodeBoarding/CodeBoarding for local analysis, automation, and CI workflows. VS Code extension https://marketplace.visualstudio.com/items?itemName=Codeboarding.codeboarding for in-editor visual architecture. GitHub Action https://github.com/marketplace/actions/codeboarding-diagram-first-documentation to keep diagrams updated in CI. - Languages: Python, TypeScript, JavaScript, Java, Go, PHP, Rust, C . - LLM providers: OpenAI, Anthropic, Google, Vercel AI Gateway, AWS Bedrock, Ollama, OpenRouter, and more. - Visualized 800+ open-source repositories. - Browse generated examples in GeneratedOnBoardings https://github.com/CodeBoarding/GeneratedOnBoardings . - Try the hosted explorer at codeboarding.org/diagrams https://codeboarding.org/diagrams . If you want to improve CodeBoarding, open an issue https://github.com/CodeBoarding/CodeBoarding/issues or send a pull request. We welcome improvements to analysis quality, output generators, integrations, and developer experience. CodeBoarding is building an open standard for code understanding: a visual, accurate, high-level representation of a codebase that both humans and agents can use.