Congratulations on the release!
Could you add fff to the benchmarks?
Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
21–30 of 187 posts
Re: Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
#22I'd be interested in seeing actual agent benchmarks (eg CC or Copilot CLI with grep removed and this tool instead). For example, I have explored RTK and various LSP implementations and find that the models are so heavily RL'd with grep that they do not trust results in other forms and will continually retry or reread, and all token savings are lost because the model does not trust the results of the other tools.
Codex CLI is quite happy running RTK. Well with GPT 5.5 xhigh anyway
One thing that irks me is that when it doesn't support eg. a cli flag of find, it gives an error message rather than sending the full output of the command instead. Then the agent wastes tokens retrying, or worse, doesn't even try because the prompting may make them afraid to not run commands without rtk
Re: Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
#23Shouldn’t it be a part of the harness at least for local codebase? I wonder how many harnesses are doing that already.
Re: Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
#24How does this compare with colgrep?
Re: Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
#25Shouldn’t it be a part of the harness at least for local codebase? I wonder how many harnesses are doing that already.
I'm playing with PI as a custom harness ( for Claude code because that what is provided to me )
I will try that ! It make sense and I'm curious to see results, for this or any similar projects mentioned in the thread
Re: Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
#26Shouldn’t it be a part of the harness at least for local codebase? I wonder how many harnesses are doing that already.
I'm playing with PI as a custom harness ( for Claude code because that what is provided to me ) I will try that ! It make sense and I'm curious to see results, for this or any similar projects mentioned in the thread
allegedly this one is good for PI
https://pi.dev/packages/@ff-labs/pi-fff
Re: Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
#27I'd be interested in seeing actual agent benchmarks (eg CC or Copilot CLI with grep removed and this tool instead). For example, I have explored RTK and various LSP implementations and find that the models are so heavily RL'd with grep that they do not trust results in other forms and will continually retry or reread, and all token savings are lost because the model does not trust the results of the other tools.
Codex CLI is quite happy running RTK. Well with GPT 5.5 xhigh anyway One thing that irks me is that when it doesn't support eg. a cli flag of find, it gives an error message rather than sending the full output of the command instead. Then the agent wastes tokens retrying, or worse, doesn't even try because the prompting may make them afraid to not run commands without rtk
how effective is RTK for you? worth using?
Re: Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
#28Better than grep obviously, but how does this compare to existing LSPs?
Re: Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
#29I'd be interested in seeing actual agent benchmarks (eg CC or Copilot CLI with grep removed and this tool instead). For example, I have explored RTK and various LSP implementations and find that the models are so heavily RL'd with grep that they do not trust results in other forms and will continually retry or reread, and all token savings are lost because the model does not trust the results of the other tools.
I just put something in my global CLAUDE.md (under ~/.Claude) asking it to use the LSP instead of grep and have never had this issue since.
Re: Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep
#30I'd be interested in seeing actual agent benchmarks (eg CC or Copilot CLI with grep removed and this tool instead). For example, I have explored RTK and various LSP implementations and find that the models are so heavily RL'd with grep that they do not trust results in other forms and will continually retry or reread, and all token savings are lost because the model does not trust the results of the other tools.
I just put something in my global CLAUDE.md (under ~/.Claude) asking it to use the LSP instead of grep and have never had this issue since.
My q would have been this. Lsp solved this no?