Jev in production › Search, ranking and matching
Local code search served over MCP to Codex, Claude Code and OpenCode; Jev ranks the selected source snippets the agent reads. Across 162 paired sessions, agents used 13–44% fewer tokens with it (author).
Help your coding agent find code faster and use fewer tokens.
Oko gives Claude Code, Codex, Cursor, OpenCode and Pi a better code search. When you ask your agent about your code, Oko has already found the relevant source, so the agent spends fewer rounds searching and reading files it does not need.
Nine coding tasks on Astro, HTTPX and ripgrep, three runs each, with and without Oko. Results · Method
- Faster: about half the time in Claude Code, OpenCode and Pi; a quarter less in Codex. - Cheaper: 33–44% fewer tokens with every tool we measured. - Fewer detours: 65–89% fewer tool calls. - Better ranking: puts the right file first more often than any published method on Agent Retrieval Bench. - Local first: search runs on your machine; only the...
For the project's own README, linking back here: