Jev in production › Search, ranking and matching

oko (bartlomein)

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).

Open on GitHub ↗

13–44% fewer tokensmeasured against a baseline, as published by the source
Use
Search, ranking and matching
Industry
Developer tools
Form
Open-source tool
Stage
Beta
Plugs into
Claude Code, Codex, OpenCode
Listed
2026-09-20
Found via
github
Repository
bartlomein/oko
Stars
9
Forks
2
Last push
2026-10-02
Language
Rust
License
MIT

The README opens with

Help your coding agent find code faster and use fewer tokens.

Oko helps Codex, Claude Code, and OpenCode spend less time searching and fewer tokens reading irrelevant code. It delivers relevant source snippets through MCP, and answers a code question as you send it, so your agent can get to the task sooner. Gains vary by task and coding tool.

Benchmark What it measures Oko --- --- --- Our agent sessions Codex, OpenCode and Claude Code on nine tasks, with and without Oko 60–63% fewer tokens, 47–58% faster, 75–86% fewer tool calls Sense's agent benchmark Claude Opus 4.7 on six multi-step tasks, run against Sense the same evening Cited recall 0.88 against Sense's 0.63, at half the cost Agent Retrieval Bench 345 code-retrieval tasks in six...

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for search, ranking and matching