5 个开源仓库搭出 Jev 决策层：路由、守卫、本地跑、训练、上线
作者整理 jev-for-all、agent-jev、jev-rs、typed-decisions、jev-usecases 五个开源项目，让 agent 用几美分做决策而非烧前沿 token。
this Jev stack is f*cking crazy 5 open-source repos that let your agent make decisions for cents instead of burning frontier tokens. each one handles a different part of the job: ROUTE > jev-for-all - Jev picks which skill to load and which tools your coding agent gets. 64 requests, 0 wrong picks, ~$0.0001 per decision http://github.com/emirbartu/jev-for-all GUARD > agent-jev - a 0.6B model that reads diffs, logs and traces and answers typed questions in ~60 ms. zero generated tokens. ships with a Claude Code hook that gates every tool call http://github.com/malevrigns/agent-jev RUN LOCAL > jev-rs - a Jev-compatible engine in Rust. plug in any local model, state gets prefilled once, every question is answered from probabilities. 75 ms per question on a Mac http://github.com/yijunyu/jev-rs TRAIN > typed-decisions - build your own Jev-style model. DeBERTa version hits 85.5% accuracy at 42 ms, and training cost $0.26 http://github.com/kotoba-lang/typed-decisions SHIP > jev-usecases - 36 production harnesses: support triage, fraud, invoices, guardrails, SOC agents. every decision lands in auto, confirm, human or block by confidence http://github.com/kenhuangus/jev-usecases the cool part isn't any single repo. it's that your agent can now: pick the right skill -> gate its own tool calls -> run offline -> learn your decisions -> ship with confidence bands your LLM doesn't need to think about every yes or no anymore. the decision layer is already on GitHub. you just plug it in. bookmark this before you build your next agent.
这条是引用着另一条写的：x.com/thegreatest_sv/status/2102802378378621355