RLM Tools

A persistent Python sandbox that keeps codebase exploration data server-side instead of dumping it into your context window. You get three tools: rlm_start to open a session on a directory, rlm_execute to run Python with built-in helpers like grep, read_file, and glob_files, and rlm_end to clean up. Variables persist across execute calls so you can grep for patterns, filter results, read matches, and build summaries incrementally. Only your print statements come back to the model. Benchmarks show 25-35% context reduction in typical workflows and up to 99% savings when exploring large codebases. Reach for this when your agent burns half its context budget reading files it never needed to see in full.