A fast Rust tool to serialize text files in a repo for LLM consumption.
yek is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view bodo-run/yek --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
Repository setup guidance
Strong trust signals; still review the README and permissions before production use.
Last commit was about 96 days ago.
2448 GitHub stars indicate community interest.
10 open issues signal maintenance load.
Universal AI context generator that saves thousands of tokens per conversation in Claude Code, Cursor, Copilot, and more.
One command gives AI agents instant codebase context, replacing 50,000+ tokens of exploration with ~250 tokens.
A memory layer for coding agents that stores and retrieves repo context, conventions, and invariants.
yek takes all text files in a directory and combines them into one file, making it easy to feed code to an LLM. It respects .gitignore, ranks files by importance using Git history, and can cap output size. You can pipe the output directly to your clipboard or another tool.
yek is a high-performance Rust CLI tool that serializes text-based files from a repository or directory into a single output, optimized for Large Language Model (LLM) consumption. It automatically respects .gitignore rules, uses Git history to infer file importance (more important files appear later in the output, where LLMs focus more), and detects binary or large files to skip. yek supports glob patterns, multiple input paths, and configurable output size limits (byte or token-based). It can stream output to stdout when piped, or write to a file. Configuration via yek.yaml allows customization. The tool is designed to be fast and efficient, making it ideal for developers who need to quickly prepare code context for AI assistants.
A fast Rust tool to serialize text files in a repo for LLM consumption.
Developers who frequently use LLMs for code assistance and need to provide context., DevOps engineers automating code analysis or documentation generation., Open-source maintainers wanting to share repository content efficiently.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Output may include sensitive information if the repository contains secrets; ensure .gitignore is properly configured. Large repositories may produce very large output files; use size caps to avoid issues.
Similar or complementary options to evaluate include codesight, Stacklit, gps.
Aug 20, 2026
MIT license detected.
2 security/trust notes recorded.
Setup difficulty is 1/5.
2,448
Stars
65
Forks
10
Issues
MIT
License