`Semble`, code search for agents using 98% fewer tokens than grep
Agents get only the relevant code chunks instead of reading whole files. If the latency claim holds in real repos, this is worth testing for repo-aware coding workflows.
Sembleaccepts natural-language and code queries, then returns only the snippets likely needed by the agent.- The headline claim is 98% fewer tokens than
grepplus file reads, directly cutting context spend. - Average repository indexing/search is listed around 250ms, so it fits interactive agent loops if accurate.
- Best use case: wiring it into custom agents or CLI flows where
rgfinds too much and full-file reads waste context.