# yamadashy/repomix

📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.

Repository: https://github.com/yamadashy/repomix
Canonical: https://ross.abutalabs.com/products/repomix
Homepage: https://repomix.com
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, llm, generative-ai, chatgpt, claude, developer-tools, chatbot, gpt, openai, javascript, nodejs, typescript, anthropic, gemini, language-model, artificial-intelligence, genai, deepseek, llama, mcp
Last push: 2026-08-26T14:06:23+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 84, longevity 55
- inputs: {"age_days": 781, "days_push": 7, "days_rel": 25, "gap_med": 6, "n_releases_24m": 82}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 28071, forks 1499 (observed 2026-08-28T04:11:48.092282+00:00)

## What it is
Repomix is a CLI tool (and web service) that packs an entire repository into a single AI-friendly file in XML, Markdown, or plain text formats for feeding to LLMs. It offers git-aware file selection, Tree-sitter-based code compression, token counting, secret detection via Secretlint, and an MCP server mode.

## Use cases
- pack my codebase into a single file for ChatGPT or Claude
- prepare repository context for an LLM code review
- count tokens for my repo before sending it to an LLM
- strip comments and compress code signatures to reduce LLM token usage
- detect API keys and secrets before sharing code with AI tools
- give an AI assistant access to my whole repository via MCP

## When to choose
- you need to share a full codebase with LLMs or AI coding assistants
- you want token counts and AI-optimized output formats like XML
- you need automatic secret detection before uploading code
- you want an MCP server that exposes repository packing to AI agents

## When to avoid
- you need real-time code indexing or semantic search rather than a one-shot file pack
- your repository is too large to fit within LLM context limits even after compression
- you only need to share a few files, where copy-paste is simpler

## Facets
- artifact type: cli-tool
- maturity: active
- function: developer-tools, llm-inference, prompt-engineering, security, cli, mcp
- domain: developer-tools, artificial-intelligence, large-language-models, security
- platform: cli, cross-platform, windows
- tags: codebase-packer, llm-context, tree-sitter, token-counting, secretlint, git-aware, ai-friendly-formats, command-line, nodejs, macos, linux

## Member repositories
- yamadashy/repomix (main) score 85

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:48.092282+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:54:27.722591+00:00, confidence not recorded.
  - readme: https://github.com/yamadashy/repomix (fetched 2026-08-28T04:11:48.092282+00:00, sha 7648ef964e01)
  - homepage: https://repomix.com (fetched 2026-08-29T07:51:30.847510+00:00, sha cc34170cbc03)
  - site_page: https://repomix.com/guide/security (fetched 2026-08-29T07:51:30.856850+00:00, sha 54b521076a94)
  - registry_npm: https://registry.npmjs.org/repomix (fetched 2026-08-29T07:51:30.859389+00:00, sha 191468de7eaf)
- Data as of 2026-08-30T08:39:29.467469+00:00.