Coding agents make hundreds of small judgment calls per session: which tool output is still relevant, how hard the next turn is, which review finding matters. Those calls are a natural fit for Jev, which answers in well under a second and costs a tiny fraction of a frontier-model call.
The projects here keep the heavy model for writing code and hand the repetitive yes/no and pick-one decisions to Jev. Context compaction and per-turn routing are the most popular patterns so far.
tamaratran/fast-jev-compaction
Claude Code plugin that replaces the compaction summary with Jev decisions. Every tool call and result is scored; stale ones are dropped or truncated, and everything kept stays verbatim.
thruwire/foreman
Puts Jev as a fast supervisor above slower coding agents such as Codex, starting from a ticket, spec, or bug report.
devagrawal09/jev-review
Staged code-review workflow with a local dashboard. Jev triages correctness, security, reliability, compatibility, and test risk, then hands the important findings to a heavier model.
NiazMorshed2007/jev-review
Local-first MCP server for continuous software-quality review by coding agents.
Dicklesworthstone/skillranker
Rust CLI that ranks which agent skills fit the next step from live session context, with Claude Code hooks.
0xNatoshi/jev-codex-router
Picks the model, reasoning depth, and speed mode for every Codex turn based on how hard Jev judges it to be. The author reports about 60% lower cost when replaying 237 real turns.
GhalebDweikat/winnow
Context sieve for Claude Code. Jev judges each tool result (Read, Bash, Grep output) for relevance before it enters the context window.
huntedman/JevLint
Checks code against conventions written in plain English, in a write-check-fix loop with your coding agent.
devagrawal09/jev-code
Bounded Jev workflows for coding agents.
New Jev releases, pricing changes, and the best new projects, once a week. No spam; unsubscribe anytime.
Powered by Buttondown. See our privacy policy.