Does this support any language or is it limited to a specific set of languages?
For chunking Semble supports all languages supported by tree-sitter-language-pack. The models we train are trained on 6 languages, but can handle way more.
Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
61–70 of 187 posts
Re: Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
#62How does this compare with colgrep? https://github.com/lightonai/next-plaid/tree/main/colgrep
The comparison is in the benchmarks, see the README
Re: Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
#63Semantic code search seems like a useful tool for a human too. Not just for agents.
Yeah I agree. I have used semble to quickly index a large monorepo and just ask a question about it, it surfaced the right files pretty quickly. Although without an IDE, it's difficult to display them in nice way
Re: Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
#64Nice, this sounds great. I want to mention a related issue here, which is that on small codebases, Claude spends a lot of time looking for stuff when it could have just dumped the whole codebase into the context in one go and used very little tokens. I found a nice workaround which is that you can just dump the whole directory into context, as a startup hook. So then Claude skips the "fumble around blindly in the dar…
This is true, agents just don't know a lot about the things they're looking at, e.g., the number of files, file sizes, etc.
Although for small codebases it also holds that whatever you would like to find it easy to find, so search still might help you with cost
Re: Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
#65Seems like a cool idea so I decided to play with it a bit. The test I ran was in the browsercode ( https://github.com/browser-use/browsercode ) repo with the following prompt: "Answer this question by only using the `semble` CLI (docs below): > What tools does Browsercode provide to the agent other than the base OpenCode tools? Provide the exact schema for tool input and tool output and briefly summarize what they do…
Wow awesome, thanks for sharing! This is really useful and very much like the experiments we want to be doing in the near future
Re: Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
#66Earlier quoted context omitted.
Or tools like `ck`: https://beaconbay.github.io/ck/
Try running both on the CK codebase. CK takes like 15 minutes to index itself and gives hundreds of completely irrelevant doc comments as results for “run model on CPU” query. Semble indexes for like 3 seconds and prints out the actual code that runs the model on the CPU.
You didn’t use `ck` directly, you instructed Claude Code to use `ck`, right?
Re: Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
#67Cool project. I built a custome IDE and coding agent harness and will integrate this into it. If you’re interested in a collaboration, I’d be happy to share revenue to sponsor your open source repo.
Re: Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
#68The instructions on how to install and use it could use some work. I did eventually install it. Will try it later and report back.
Re: Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
#69The instructions on how to install and use it could use some work. I did eventually install it. Will try it later and report back.
Oh sorry that happened. Feel free to open an issue or report it here
Re: Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
#70I did some evals with pi and GPT 5.5. I tested RTK on / headroom on / both on / both off (all with the standard pi system instructions and no AGENTS.md). I forget the exact tests I used (a couple of the standard agent evals that people use, one python and one typescript because those are what I use). I don't claim it was an exhaustive test, or even a good one. It's possible I could have spent a day or so tuning my AG…
with AI the "they could so they never wondered if they should" will be a very frequent thing.
This is a bit rude.
We didn't generate this project, we wrote it, a lot of it manually, and trained custom models. We'd been working in the real-time retrieval space for a while, and we thought coding was a good fit for this specific technology.