{"slug": "codeboarding-interactive-architecture-diagrams-for-codebases", "title": "Codeboarding – Interactive architecture diagrams for codebases", "summary": "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.", "body_md": "See what your AI is building before it breaks.\n\nCodeBoarding 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.\n\n[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)\n\nInstall the extension from Open VSX.\n\n- Keep architecture visible while agents code.\n- Review AI-generated changes with system context before they turn into hidden debt.\n- Understand large repositories faster with layered diagrams and component breakdowns.\n- Share the same visual model across local workflows, IDEs, pull requests, and docs.\n\n- High-level system architecture diagrams.\n- Deeper component diagrams for important subsystems.\n- Markdown documentation in\n`.codeboarding/`\n\n. - Mermaid output that is easy to embed in docs and PRs.\n- Incremental updates when only part of the codebase changes.\n\n```\ngraph LR\n    Application_Orchestrator_Repository_Manager[\"Application Orchestrator & Repository Manager\"]\n    LLM_Agent_Core[\"LLM Agent Core\"]\n    Static_Code_Analyzer[\"Static Code Analyzer\"]\n    Agent_Tooling_Interface[\"Agent Tooling Interface\"]\n    Incremental_Analysis_Engine[\"Incremental Analysis Engine\"]\n    Documentation_Diagram_Generator[\"Documentation & Diagram Generator\"]\n    Application_Orchestrator_Repository_Manager -- \"Orchestrator initiates analysis workflow, leveraging incremental updates based on detected code changes.\" --> Incremental_Analysis_Engine\n    Application_Orchestrator_Repository_Manager -- \"Orchestrator passes project context and triggers the main analysis workflow for the LLM Agent.\" --> LLM_Agent_Core\n    Incremental_Analysis_Engine -- \"Incremental engine requests static analysis for specific code segments (new or changed).\" --> Static_Code_Analyzer\n    Static_Code_Analyzer -- \"Static analyzer provides analysis results to the incremental engine for caching.\" --> Incremental_Analysis_Engine\n    LLM_Agent_Core -- \"LLM Agent invokes specialized tools to interact with the codebase and analysis data.\" --> Agent_Tooling_Interface\n    Agent_Tooling_Interface -- \"Agent tools query the static analysis engine for detailed code insights.\" --> Static_Code_Analyzer\n    Static_Code_Analyzer -- \"Static analysis engine provides requested data to the agent tools.\" --> Agent_Tooling_Interface\n    LLM_Agent_Core -- \"LLM Agent delivers structured analysis insights for documentation and diagram generation.\" --> Documentation_Diagram_Generator\n    click Application_Orchestrator_Repository_Manager href \"https://github.com/CodeBoarding/CodeBoarding/blob/main/.codeboarding/Application_Orchestrator_Repository_Manager.md\" \"Details\"\n    click LLM_Agent_Core href \"https://github.com/CodeBoarding/CodeBoarding/blob/main/.codeboarding/LLM_Agent_Core.md\" \"Details\"\n    click Static_Code_Analyzer href \"https://github.com/CodeBoarding/CodeBoarding/blob/main/.codeboarding/Static_Code_Analyzer.md\" \"Details\"\n    click Agent_Tooling_Interface href \"https://github.com/CodeBoarding/CodeBoarding/blob/main/.codeboarding/Agent_Tooling_Interface.md\" \"Details\"\n    click Incremental_Analysis_Engine href \"https://github.com/CodeBoarding/CodeBoarding/blob/main/.codeboarding/Incremental_Analysis_Engine.md\" \"Details\"\n    click Documentation_Diagram_Generator href \"https://github.com/CodeBoarding/CodeBoarding/blob/main/.codeboarding/Documentation_Diagram_Generator.md\" \"Details\"\n```\n\nFor a deeper architecture walkthrough, see [ .codeboarding/overview.md](/CodeBoarding/CodeBoarding/blob/main/.codeboarding/overview.md).\n\n```\nuv sync --frozen\nsource .venv/bin/activate  # On Windows: .venv\\Scripts\\activate\npython install.py\npython main.py full --local /path/to/repo\n```\n\nRequires **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:\n\n```\npipx install codeboarding --python python3.12\ncodeboarding-setup\ncodeboarding full --local /path/to/repo\n```\n\nOr, if you prefer pip, install into a virtual environment (not the global Python):\n\n```\npip install codeboarding\ncodeboarding-setup\ncodeboarding full --local /path/to/repo\n```\n\nOutput is written to `/path/to/repo/.codeboarding/`\n\n.\n\n`python install.py`\n\nand `codeboarding-setup`\n\ndownload language server binaries to `~/.codeboarding/servers/`\n\n, shared across projects. Node.js (and its bundled `npm`\n\n) is required for the Python, TypeScript, JavaScript, and PHP language servers; if neither `node`\n\nnor `CODEBOARDING_NODE_PATH`\n\nis set, setup downloads a pinned Node.js runtime into `~/.codeboarding/servers/nodeenv/`\n\nautomatically.\n\nOn first run, CodeBoarding creates `~/.codeboarding/config.toml`\n\n. Set one provider there or use environment variables.\n\n```\n[provider]\n# openai_api_key            = \"sk-...\"\n# anthropic_api_key         = \"sk-ant-...\"\n# google_api_key            = \"AIza...\"\n# vercel_api_key            = \"vck_...\"\n# aws_bearer_token_bedrock  = \"...\"\n# ollama_base_url           = \"http://localhost:11434\"\n# openrouter_api_key        = \"sk-...\"\n\n[llm]\n# agent_model   = \"gemini-3-flash\"\n# parsing_model = \"gemini-3-flash\"\n```\n\nShell environment variables such as `OPENAI_API_KEY`\n\n, `ANTHROPIC_API_KEY`\n\n, `GOOGLE_API_KEY`\n\n, and `OLLAMA_BASE_URL`\n\ntake precedence over the config file. For private repositories, set `GITHUB_TOKEN`\n\nin your environment.\n\n```\n# Analyze a local repository\npython main.py full --local ./my-project\n\n# Increase diagram depth\npython main.py full --local ./my-project --depth-level 2\n\n# Re-analyze only changed parts when possible\npython main.py incremental --local ./my-project\n\n# Update a single component by ID\npython main.py partial --local ./my-project --component-id \"1.2\"\n\n# Analyze a remote GitHub repository\npython main.py full https://github.com/pytorch/pytorch\n```\n\n[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.\n\n- Languages: Python, TypeScript, JavaScript, Java, Go, PHP, Rust, C#.\n- LLM providers: OpenAI, Anthropic, Google, Vercel AI Gateway, AWS Bedrock, Ollama, OpenRouter, and more.\n\n- Visualized 800+ open-source repositories.\n- Browse generated examples in\n[GeneratedOnBoardings](https://github.com/CodeBoarding/GeneratedOnBoardings). - Try the hosted explorer at\n[codeboarding.org/diagrams](https://codeboarding.org/diagrams).\n\nIf 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.\n\nCodeBoarding is building an open standard for code understanding: a visual, accurate, high-level representation of a codebase that both humans and agents can use.", "url": "https://wpnews.pro/news/codeboarding-interactive-architecture-diagrams-for-codebases", "canonical_source": "https://github.com/CodeBoarding/CodeBoarding", "published_at": "2026-05-27 20:29:22+00:00", "updated_at": "2026-05-27 20:44:19.728506+00:00", "lang": "en", "topics": ["ai-tools", "ai-products", "ai-agents", "large-language-models", "ai-infrastructure"], "entities": ["CodeBoarding", "Open VSX", "VS Code", "GitHub", "Discord", "Mermaid"], "alternates": {"html": "https://wpnews.pro/news/codeboarding-interactive-architecture-diagrams-for-codebases", "markdown": "https://wpnews.pro/news/codeboarding-interactive-architecture-diagrams-for-codebases.md", "text": "https://wpnews.pro/news/codeboarding-interactive-architecture-diagrams-for-codebases.txt", "jsonld": "https://wpnews.pro/news/codeboarding-interactive-architecture-diagrams-for-codebases.jsonld"}}