# mohsen1/yek

A fast Rust based tool to serialize text-based files in a repository or directory for LLM consumption

Repository: https://github.com/mohsen1/yek
Canonical: https://ross.abutalabs.com/products/yek
Language: Rust
License: MIT
License Family: permissive
Topics: ai, cli, large-language-models, llm, rust-lang, serialization
Last push: 2026-06-29T16:45:04+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 90, release rhythm 90, longevity 42
- inputs: {"age_days": 599, "days_push": 65, "days_rel": 65, "gap_med": 0, "n_releases_24m": 40}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2474, forks 65 (observed 2026-08-28T04:06:54.894726+00:00)

## What it is
Yek is a fast Rust CLI tool that serializes text files in a repository or directory into a single stream or chunked output optimized for LLM consumption. It respects .gitignore rules, uses Git history to prioritize important files, and supports token/size caps, glob patterns, and YAML configuration.

## Use cases
- serialize a codebase into a single file to paste into an LLM prompt
- prepare repository context for AI coding assistants
- cap repository output to a token limit for a context window
- pipe source files to clipboard for sharing with a chatbot
- bundle selected files or globs into one text chunk
- prioritize important files last in LLM context

## When to choose
- you need to feed a whole repo or directory to an LLM within a token budget
- you want gitignore-aware, git-history-prioritized file bundling with fast Rust performance
- you want zero-config defaults with optional YAML customization

## When to avoid
- you need semantic code parsing or AST-aware chunking
- you need to serialize binary or non-text assets
- you want a GUI or IDE-integrated context builder

## Facets
- artifact type: cli-tool
- maturity: active
- function: serialization, cli, developer-tools
- domain: developer-tools, large-language-models, files
- platform: cli, cross-platform, rust, windows
- tags: llm-context, codebase-serialization, git-aware, context-window, prompt-preparation, command-line, macos, linux

## Member repositories
- mohsen1/yek (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:54.894726+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 2026-08-30T02:28:26.553567+00:00, confidence not recorded.
  - readme: https://github.com/mohsen1/yek (fetched 2026-08-28T04:06:54.894726+00:00, sha 98cb6a424b4e)
  - registry_crates: https://crates.io/api/v1/crates/yek (fetched 2026-08-29T10:10:24.733849+00:00, sha 7246835e4710)
- Data as of 2026-08-30T08:39:29.467469+00:00.