I Tested 9 AI Agent Search Tools

Try Control Plane ➡️ https://htfctr.to/nMuOqip

XERJ hit number one on GitHub promising to stop coding agents from burning tokens, so I plugged it into a large TypeScript repo I work in every day and the results weren't what I expected. That sent me down a rabbit hole testing nine agent search tools head to head on my own codebase, with exact run counts, token numbers, and setup costs. If you're thinking about adding a search tool to your agent, watch this first and save yourself the install.

00:00 Intro

00:26 What XERJ actually is

01:15 First real-world test

02:44 Rethinking the test

03:15 Nine-tool search benchmark

03:59 Benchmark results

05:46 What I chose

06:16 Limits of the test