Skip to content
repository radar
Models & Inference

🧰Yek

ACTIVE FLATLINED

mohsen1/yek

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

⭐ Popular: 2k stars, gaining about 2 a week

View on GitHub ↗

repo profile

vintage 2025 1 year old
delivery product
language Rust
license MIT

momentum

total stars 2k
stars added last week +2
binary downloads 271 total · GitHub releases
used by 3 repos & packages
commits / week 0 cooling · -100% vs prior mo
issues closed 79% closed same-day, median
contributors 11
release cadence quarterly
last activity 1mo ago

durability

backing community / independent
openness permissive
bus factor 1 solo
top-author share 86% 6 mo

bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.

since we covered it

monthly average + 30/mo (+1%/mo) · + 471 total since PR#7

why it's a big deal

  • Packs a whole repository into a single serialized text stream that a language model can read in one pass, replacing manual copy-paste of files into a prompt.
  • Helps anyone feeding code to an LLM, developers, prompt authors, tooling builders, by respecting.gitignore and skipping binary and oversized files so only relevant text-based content is included.
  • Fits output to a fixed budget by capping on byte size or token count and dropping the files that will not fit, keeping the more important ones within the context window.

under the hood

  • Written in Rust and run as a CLI that streams to stdout when piped or writes files otherwise, and can process multiple directories, globs, and individual files in one invocation.
  • Uses Git history to score file importance and deliberately orders more important files last, since LLMs weight later context more heavily, with a configurable git-boost weighting.
  • Configured through a yek.yaml file covering max_size, token limits, ignore and unignore patterns, priority rules, custom binary extensions, and output options such as JSON, line numbers, and a file tree header.

Radar summary, generated from the project's public sources

star history

PR#7 · 2k2k now Jan 2025Aug 2026
  1. PR#7 2k 2025-04-30
  2. now 2k + 471 since first covered

curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.

understory

Output and attention are roughly in balance.

+4 understory score output 31 · clout 27
Aug 2025 Jul 2026
  • output, commits & releases
  • clout, star velocity

output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →

covered in

  • PR#7 2025-04-30 below the radar

    A Fast Rust-Based Tool to Serialize Text-Based Files for LLM Consumption

similar projects

compare these →
  • 🧩 TensorZero

    4.7× the stars

    TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.

    12k OFF THE RADAR
  • 🦙 LLaMA-Factory

    Python · 30× the stars

    Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

    74k ACTIVE
  • 🖥️ Open WebUI

    Python · 60× the stars

    User-friendly AI Interface (Supports Ollama, OpenAI API,...)

    149k ACTIVE

comments

Sign in with GitHub to add your blip on Yek.

loading comments…