1
llm-course
Shares tags: ai
AI ToolDead Man Walking
repomix Review
Repomix packages your codebase into a single, AI-friendly file for seamless analysis by Large Language Models.
shipped Apr 17, 2026updated May 27, 2026aifreemium
1Packages entire code repositories into a single, AI-friendly file for LLM consumption.
2Supports multiple output formats including XML, Markdown, JSON, and Plain text.
3Reduces token usage by approximately 70% through Tree-sitter intelligent code compression.
4Nominated for JSNation Open Source Awards 2025 in the 'Powered by AI' category.
Stork Quadrant
Dead Man Walking· 2/100
An LLM can do most of what this tool's UI promises. No moat, no agent presence.
“Repomix is a pure convenience wrapper around file I/O and text formatting — tasks Claude and other LLMs can already do natively with file system access or simple prompting. The core value ("pack my repo for an LLM") evaporates the moment Claude gets native code repository integration or when users realize they can paste a repo structure and ask an LLM to handle it. This tool dies the day Claude's context window makes selective packing unnecessary or when Claude can directly ingest git repos.”
Defensibility · 0/100
- Physical-world coupling
- Regulatory moat
- Network liquidity
- Proprietary refreshing data
- High-trust catastrophic workflows
- Multi-party coordination
- Brand / community / taste
An LLM alone could replace
- Parse a repository structure and generate a text summary of files and directories
- Format code files into a single concatenated document for LLM context windows
- Filter and exclude common non-essential files (node_modules, .git, etc.)
- Generate a token count estimate for the packaged codebase
Agent-Readiness · 5/100
- Verified MCP
- Listed on agent surfaces
- Usage-based pricing
- Headless agent auth
- Public OpenAPI
- Active changelog
- llms.txt— https://repomix.com/llms.txt
How to defend
Become the agent-native layer: stop being a UI and become the CLI/API that agents call to prepare code context before reasoning. Alternatively, own a vertical (e.g., "repomix for security audits" with built-in SAST rules and liability insurance) where the output format and filtering rules are so specialized that an LLM alone can't replace the domain logic.
- Ship an MCP server and list it on Stork — biggest single point gain (+25).
- Get listed in the Anthropic MCP registry, Cursor, or Claude Desktop (+20).
- Add a usage-based or per-call tier; per-seat-only pricing dies when agents replace seats (+15).
- Expose API-key auth with a self-serve sandbox tier; remove sales-call gates (+15).
- Publish an OpenAPI spec at /openapi.json or /.well-known/openapi (+10).
repomix at a Glance
Connect
</>Embed "Featured on Stork" Badge▼
<a href="https://www.stork.ai/en/repomix" target="_blank" rel="noopener noreferrer"><img src="https://www.stork.ai/api/badge/repomix?style=dark" alt="repomix - Featured on Stork.ai" height="36" /></a>
[](https://www.stork.ai/en/repomix)
overview
What is repomix?
repomix is an AI tool that enables developers and AI engineers to package entire code repositories into a single, AI-friendly file. This addresses the challenge of Large Language Model (LLM) context window limitations, allowing AI assistants to understand the full project context without manual file exploration. The tool transforms codebases into structured, AI-optimized formats such as XML, Markdown, or plain text, which can be efficiently processed by various AI platforms including Claude, ChatGPT, Gemini, and Grok. Its primary function is to provide comprehensive codebase context for tasks like architecture reviews, refactoring, debugging, and security analysis.
quick facts
Quick Facts
| Attribute | Value |
|---|---|
| Developer | Open-source project |
| Business Model | Freemium |
| Pricing | Freemium |
| Platforms | CLI (Node.js), Docker, GitHub Actions, Browser Extensions (Chrome), VSCode Integration |
| API Available | No |
| Integrations | GitHub Actions, Secretlint, Tree-sitter, Model Context Protocol (MCP) Server |
features
Key Features of repomix
Repomix provides a robust set of features designed to optimize codebases for AI analysis and interaction, addressing common challenges in large language model integration.
- 1Packs entire code repositories into a single, AI-friendly file.
- 2Supports multiple output formats including XML, Markdown, JSON, and Plain text.
- 3Allows for precise inclusion and exclusion of files using glob patterns.
- 4Intelligent code compression utilizing Tree-sitter to reduce token usage by approximately 70% while preserving context.
- 5Git-aware functionality, automatically respecting `.gitignore` files for relevant content inclusion.
- 6Security-focused with integrated Secretlint for detecting and preventing sensitive information inclusion.
- 7Provides token counts for individual files and the entire repository, aiding in context window management.
- 8Offers a command-line interface (CLI) for processing both local and remote repositories.
- 9Supports Docker usage for isolated and consistent environment deployments.
- 10Integrates with GitHub Actions for automated codebase packing within CI/CD workflows.
- 11Functions as a Model Context Protocol (MCP) server, enabling direct codebase interaction for AI assistants.
- 12Provides browser extensions (e.g., Chrome) for one-click access from GitHub repository pages and VSCode integration.
use cases
Who Should Use repomix?
Repomix is designed for individuals and teams requiring comprehensive AI analysis of codebases, facilitating various development, security, and documentation tasks.
- 1Developers: For comprehensive code reviews, refactoring, bug investigation, and AI-driven incremental development across entire projects.
- 2AI Engineers: For feeding complete codebases to Large Language Models (LLMs) like Claude, ChatGPT, Gemini, and Grok for in-depth analysis and knowledge extraction.
- 3Security Analysts: For comprehensive security scanning and vulnerability analysis of codebases, including third-party library checks.
- 4Technical Writers and Authors: For automated documentation generation from code and creating knowledge datapacks from written content for AI-powered Q&A systems.
pricing
repomix Pricing & Plans
Repomix operates on a freemium model. The core command-line interface (CLI) tool is open-source and freely available for use, allowing users to package repositories without cost. Specific premium tiers or paid services are not publicly detailed, with the primary utility residing in its open-source CLI.
- 1Freemium: The core CLI tool is open-source and free to use, providing full functionality for packaging repositories.
competitors
repomix vs Competitors
Repomix occupies a distinct position in the landscape of tools designed to prepare codebases for Large Language Model consumption, offering specific advantages and differing in implementation from its alternatives.
1
Gitingest↗
Gitingest converts any Git repository into a simple text digest optimized for LLM prompts, offering a web interface, CLI, and browser extension for accessibility.
Similar to Repomix, Gitingest focuses on creating a single, AI-friendly text digest of a codebase. Its availability as a web service and browser extension provides alternative access methods compared to Repomix's primary CLI focus.
2
OneFileLLM is a Python-based tool designed to pack an entire repository into a single AI-friendly file, often used for feeding code to LLMs.
OneFileLLM serves the same core purpose as Repomix, packaging a repository for LLM consumption. Its Python implementation might be preferred by developers already working within the Python ecosystem, whereas Repomix is a Node.js CLI tool.
3
Yek serializes code repositories into an LLM-digestible format and claims to be significantly faster than Repomix.
Yek directly competes with Repomix by offering repository serialization for LLMs. Its claimed speed advantage could be a significant differentiator for users dealing with larger codebases or requiring faster processing times.
4
code2prompt is a Rust-based CLI tool that converts a codebase into a single LLM prompt, featuring source tree inclusion and prompt templating.
Like Repomix, code2prompt focuses on preparing a codebase for LLM prompts. Its Rust implementation may offer performance benefits, and its explicit support for prompt templating could provide more structured and customizable output for specific AI tasks.
❓
Frequently Asked Questions
+What is repomix?
repomix is an AI tool that enables developers and AI engineers to package entire code repositories into a single, AI-friendly file. This addresses the challenge of Large Language Model (LLM) context window limitations, allowing AI assistants to understand the full project context without manual file exploration.
+Is repomix free?
Yes, repomix operates on a freemium model. The core command-line interface (CLI) tool is open-source and freely available for use, allowing users to package repositories without cost.
+What are the main features of repomix?
Key features include packaging entire repositories into a single AI-friendly file, support for multiple output formats (XML, Markdown, JSON, Plain), intelligent code compression using Tree-sitter, Git-aware functionality, Secretlint integration for security, token counting, CLI for local and remote repositories, GitHub Actions integration, and Model Context Protocol (MCP) server capabilities.
+Who should use repomix?
Repomix is primarily used by developers for code reviews and debugging, AI engineers for feeding code to LLMs, security analysts for vulnerability scanning, and technical writers for documentation generation. It targets anyone needing to provide comprehensive codebase context to AI tools.
+How does repomix compare to alternatives?
Repomix differentiates itself from tools like Gitingest, OneFileLLM, Yek, and code2prompt through its Node.js CLI implementation, specific focus on Tree-sitter compression, and integration with tools like Secretlint. While competitors may offer different platforms (web, Python, Rust) or claim speed advantages, repomix provides a robust, open-source solution for AI-optimized codebase packaging.
For builders
This page is doing a job for someone else’s tool.
AI agents read it. Buyers find it. Backlinks accrue. Your tool can have one too — live in 24 hours, indexed by Claude, ChatGPT, and Perplexity, queryable via MCP.