ferret-mcp vs repomix
Codebase analysis and AI-ready repository packaging compared
ferret-mcp analyzes a repository to surface its structure, dependencies, conventions, and interfaces, with optional LLM-powered reports and answers. repomix packages repository files into structured output for AI workflows, with controls for file selection, token usage, and output format.
ferret-mcp: Analyze Codebases Through MCP
Ferret MCP gives AI assistants static codebase analysis and optional LLM-powered reports about architecture, dependencies, patterns, and APIs. It suits developers exploring unfamiliar repositories, but its quiet, single-contributor project status is worth weighing before relying on it in a team workflow.
repomix: Pack Codebases for AI Analysis
Repomix combines repository files into a structured, AI-friendly output for code review, exploration, and other LLM workflows. Use it from the CLI, website, or as an MCP server, with controls for file selection and token usage.
| ferret-mcp | repomix | |
|---|---|---|
| Language | Python | TypeScript |
| License | MIT | MIT |
| Stars | 0 | 28.7k |
| Forks | 0 | 1.6k |
| Last analyzed | Oct 9, 2026 | Oct 3, 2026 |
Key differences
- ferret-mcp focuses on describing codebase architecture and patterns, while repomix focuses on packaging repository content for AI analysis.
- ferret-mcp combines static inspection with optional LLM interpretation; repomix creates structured repository output and offers experimental Tree-sitter-based compression.
- ferret-mcp is written in Python and requires Python 3.12 or newer; repomix is written in TypeScript.
- ferret-mcp's static tools work without an LLM, while its deep reports and question answering need provider configuration; repomix offers CLI, website, and MCP server access.
- repomix supports local and remote repositories, multiple output formats, token budgets, and file filters; ferret-mcp provides analysis tools and reports through MCP.
- repomix has 28.7k stars and 1.6k forks, while ferret-mcp has 0 stars and 0 forks in the supplied project data.
Choose ferret-mcp if you…
- need structured insight into architecture, dependencies, conventions, or interfaces.
- want static repository analysis that can work without an LLM.
- need repository-context answers or deep analysis through an MCP client.
Choose repomix if you…
- want to package local or remote repositories into a single AI-friendly output.
- need control over file selection, output formats, or token budgets.
- want CLI or website access, or MCP integration for packaging codebase content.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.