Recent submissions

Comment · 5 months ago
Done some work fixing some of these issues. Please do raise issues when you find them and I'll get them fixed! (author)
Comment · 1 year ago
Sadly, not great support for Elixir from tree-sitter but it should handle them generically as text files
Comment · 1 year ago
Ruby support has been added!
Comment · 1 year ago
Nice catch- should be fixed in latest
Comment · 1 year ago
Added Ruby, but Elixir not very well supported by tree sitter
Comment · 1 year ago
coming up next.
Comment · 1 year ago
interesting - can I ask you to try a ck --index . ?
Comment · 1 year ago
BAAI/bge-small-en-v1.5 but considering switching this to google's latest gemmaembedding - it's fairly switchable.
Comment · 1 year ago
we all know rust CLI tools are better right?
Comment · 1 year ago
I'll add rust, ruby, elixir, Clojure next. It says rust as it's written in rust, sorry about that!
Comment · 1 year ago
Mainly I wrote it because I noticed Claude's "by design" use of grep meant it couldn't search the code base for things it didn't already know the name of, or find "the auth section". But equally, it's well documented that e.g. Cursor's old RAG technique wasn't that great.

My idea was to make a tool that just does a quick and simple embedding on each file, and uses that to provide a semantic alternative that is much closer to grep in nature, but allows an AI tool like Claude Code to run it from the command line - with some parameters.

Arguably could be MCP, but in my experience setting up a server for a basic tool like this is a whole lot of hassle.

I'm fairly confident that this is a useful tool for CC as it started using it while I was coding it, and even when buggy, was more than willing to work around the issues for the benefit of having semantic search!

Comment · 1 year ago
Fair comment- the initial thinking was to have both and in fact a hybrid mode too which fuses results so you can get chunks that match both semantically and on keyword search in one resultset. Later could add a reranker too.
Comment · 1 year ago
Yes- files are hashed and checked whenever you search so index should always remain up to date. Only changed files are reindexed. You can also inspect the metadata (chunking semantics, embeddings). It’s all in the .ck sidecar
Comment · 1 year ago
It supports most languages but needs a bit of tree-sitter setup to do semantic chunking. Let me know what languages you’d like added
Comment · 1 year ago
To start with just tell it- but yes Claude.md works too.

“We have a new grep semantic hybrid tool installed called ck - check it out using ck --help and take it for a spin”

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton