repomix

Orchestrates a six-phase pipeline (discovery via glob patterns and .gitignore rules, parallel file collection, security validation via Secretlint, transformation with Tree-sitter compression, template-based formatting, and tiktoken-based token counting) to pack entire repositories into single files in XML, Markdown, JSON, or Plain Text formats. Uses worker-based parallel processing to handle large codebases efficiently while maintaining structural awareness through AST parsing rather than naive concatenation.

Implements a declarative configuration system (via .repomixrc.json or CLI flags) that supports glob patterns, .gitignore integration, language-specific filters, and file size limits. The configuration loader merges CLI arguments with file-based config using a precedence hierarchy, allowing users to define complex inclusion/exclusion rules without modifying code. Supports both positive patterns (include) and negative patterns (exclude) with gitignore-style semantics.

Provides a browser-based interface for testing Repomix functionality without local installation. The web platform includes an interactive try-it interface where users can input repository URLs or paste code, configure packaging options, and preview output in real-time. Server-side API handles repository cloning and processing, with results streamed back to the browser. Supports multi-language documentation and localized UI.

Provides a browser extension that integrates Repomix directly into GitHub's web interface. Users can click a button on any GitHub repository page to package the repository without leaving GitHub. The extension communicates with the Repomix web platform API to handle processing, and provides options to download or copy the packaged output. Supports both public and private repositories (with authentication).

Provides a GitHub Action that enables automated repository packaging as part of CI/CD workflows. The action can be triggered on push, pull request, or schedule events, packaging the repository and uploading results as artifacts or committing them to the repository. Supports configuration via action inputs (format, filters, compression options) and environment variables. Integrates with GitHub's artifact storage and release systems.

Enables packaging of remote Git repositories by cloning them to a temporary directory, processing the cloned files through the standard pipeline, and cleaning up temporary storage. Supports both HTTPS and SSH Git URLs with automatic credential handling. The remoteAction() function orchestrates cloning, validation, and cleanup with error recovery for network failures or invalid repository URLs.

Exposes Repomix functionality as an MCP server that integrates directly with AI assistants like Claude. Implements MCP tools for packing repositories and retrieving packaged content, allowing AI assistants to invoke Repomix operations within their native tool-calling interface. The MCP server mode runs as a separate process that communicates with the AI assistant via JSON-RPC over stdio, enabling seamless integration without CLI invocation overhead.

Leverages Tree-sitter AST parsing to intelligently strip comments and compress code structure across 40+ programming languages. For each supported language, the system parses source code into an abstract syntax tree, identifies comment nodes, removes them while preserving code semantics, and optionally adds line numbers for reference. Unsupported languages fall back to regex-based comment stripping. This approach reduces token consumption by 20-40% compared to naive concatenation while maintaining code structure.

Integrates OpenAI's tiktoken library to calculate accurate token counts for packaged output before sending to LLMs. Provides per-file and aggregate token statistics, allowing users to understand context window consumption and optimize packaging parameters. The metrics system tracks compression ratios, file counts, and estimated costs for different LLM providers based on token counts.

Integrates Secretlint into the transformation pipeline to detect and prevent accidental exposure of secrets (API keys, credentials, tokens) in packaged output. Scans files during the transformation phase before output generation, flagging files containing detected secrets and optionally blocking packaging or redacting sensitive content. Supports configurable secret patterns and multiple secret detection rules.

Implements a template-based output generation system supporting XML, Markdown, JSON, and Plain Text formats. Each format uses language-specific templates that structure packaged content with metadata (file paths, line counts, language), making output optimized for different consumption patterns. The builder pattern allows programmatic output construction with format-specific optimizations, while templates enable user-customizable output structure.

Generates structured skill definitions that enable AI assistants to understand and invoke Repomix capabilities. Produces skill descriptions, parameter schemas, and usage examples in formats compatible with AI assistant frameworks. The system introspects Repomix configuration and capabilities to generate accurate skill definitions without manual specification, enabling AI agents to discover and use Repomix features dynamically.

Provides a command-line interface with real-time progress feedback via animated spinners and status messages. The CLI runner (cliRun.ts) orchestrates the packaging pipeline with visual feedback at each stage (discovery, collection, validation, transformation, formatting, metrics). Supports both verbose and quiet output modes, with structured logging for debugging and error reporting.