jevex

Minimal agent loop where Jev directs control flow and a LangChain chat model writes argument values and the final response.

Illustrated architecture explainer — the Jev/LLM split, a live research walkthrough, token accounting, and the limits exposed by the benchmark.

How it uses Jev

Illustrated architecture explainer — the Jev/LLM split, a live research walkthrough, token accounting, and the limits exposed by the benchmark.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to jevex

Browse all
pi-jev-router (philippdubach) project preview
A minimal Pareto-optimal OpenRouter model router for pi, based on Jev
jevXagent project preview
Agent tooling
When Jev meets LLM — Transparent proxy that makes AI coding agents 3× faster and 80% cheaper. Cut response times from 2.4s to 890ms with Line J architecture.
jev-builder-loop project preview
Agent tooling
Grok skill: Jev as a judgment sensor in a builder-agent loop (priors × probabilities → next act)
jev-mobile project preview
Browser & computer use
Fast structured Android control loops with TypeSafe Jev and Mobile MCP
dohnuts project preview
Applications
Dohnuts builds small multimodal models for direct decisions. -> System One model
jev-chat-windows-deepseek-jev project preview
Windows 微信回复助手:DeepSeek 官方生成话术,TypeSafe JEV 官方判断排序,支持可取消的 3 秒自动发送。
jevalyn project preview
SDKs & clients
The decision layer for your Rails app. A Rails-native wrapper around TypeSafe's Jev System One API: typed, calibrated decisions in your control flow.
jev-chat-jarvis-mac project preview
Browser & computer use
微信消息意图识别悬浮窗(macOS):看屏 + 本地小模型判断意图和风险,再按话术生成回复候选。纯只读、不注入微信。
jev-visual project preview
Benchmarks & research
An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos.