Jev in production › Agent context and memory

optim-jev

Claude Code plugin uses Jev for context compaction, model routing, and skill selection, reporting per-session dollar savings.

Open on GitHub ↗

The source publishes no measured number.
Use
Agent context and memory
Industry
Developer tools
Form
Open-source tool
Stage
In production
Plugs into
Claude Code
Listed
2026-10-09
Found via
github
Repository
Oqura-ai/optim-jev
Stars
6
Forks
0
Last push
2026-10-10
Language
Python
License
none stated

The README opens with

Spend fewer tokens in long Claude Code sessions—without changing how you work.

Jev-powered context compaction, model routing, and skill selection in one Claude Code plugin.

Long agent sessions accumulate stale tool output, send oversized skill catalogs, and use the main model for work a smaller model could handle. optim-jev reduces that overhead at three points while keeping Claude Code's normal workflow intact.

Each tool works independently, fails open if unavailable, and includes a stats command that reports session-level cost and savings in US dollars.

Badge

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

Listed in Jev in production

Also used for agent context and memory