Viewing profile — Bibabomas

"it works fine and this is not a bottleneck. For large projects, other parts are much slower": I don't think this is true, especially for large projects. I just ran your tool on th…

I don't understand what you mean with your first sentence. Both SemHash and Slopo are deduplication libraries right? Regardless, finding similar code is the core functionality that…

Have you compared this to https://github.com/MinishLab/semhash (or considered using that for the deduplication backend)?

Fair, many tools trade off cost for performance/adherence. So far our experience is good with Semble (at least with Anthropic/OpenAI models), but if you have any feedback feel free…

There's a "semble savings" command you can run to see token savings. It varies heavily based on the repo: in general, the larger the project the larger the savings. Output code qua…

Hey, this skepticism is fair and we share it, which is why we don't claim end-to-end agent improvements since we haven't measured those (yet). The benchmark we published measures r…

Wow, thanks for sharing, and cool that you're working on similar things! Feel free to drop any feedback on the repo if you want!

This is mostly done with the prompt. To be fair, we are still evaluating and improving this as well!

Hey, what's the issue with a disk search-lib in python specifically? The library is extremely fast. Yes, we could probably squeeze some more performance in Rust, but that's not our…

[dead]

In theory maybe, but in practice it hurts more than it helps I think. Irrelevant context makes the model more likely to reason from the wrong code (and it's slower and more expensi…

Hey, thanks for the detailed feedback. For the bug, would you mind opening an issue with your setup details? This is definitely something we want to investigate and fix. The multip…

[dead]

The 98% is vs the grep+read loop, not grep output alone. When an agent hits an unfamiliar codebase it typically does "cat file" or reads the whole thing first, at least in my exper…

What do you mean by this exactly?

Hey, we do a couple of things specifically to prevent supply-chain attacks. We use trusted publishing on PyPI, and --exclude newer for uv's package resolution. We also try to use t…

Yeah this is a good point, but it's complicated to do well since semble then has to be aware of everything else that happens in a session, which would then make it more intrusive (…

In practice this rarely happens though, at least in practice I rarely see agents "grep -C N" or something like that on files it didn't read yet. I use Claude Code and OpenCode exte…

I've had the same experience with RTK, where my agent got stuck in a loop with a faulty RTK command and could not escape it since RTK hard overwrites anything automatically. I've u…

Nice! Let us know if you have any feedback or results to share, would be happy to do the same.

Sorry to hear about the MCP integration, that's definitely something we'll look into. If you have any info about your system or how to reproduce it please let me know. Very nice to…

The first is hard to test for us unfortunately since we don't use Cursor. But the Claude thing is interesting. I think that providers (especially the ones that directly sell LLM ca…

Serena does a lot more than semble (I actually used serena before building this and didn't like how much it does by default). That also made it hard to see if it was actually worki…

Afaik many harnesses ship the "default" which is grep+read (like Claude Code). But I agree, IMO it's a weird gap. To be fair I don't think providers are that incentivised to reduce…

Interesting, will have a look at this, thanks for sharing.