Jev in production › Model and agent routing

ego-decision-layer

Replaces the per-step LLM turn in ego lite browser automation with one Jev decision to pick the next action, cutting median latency to 434ms (author).

Open on GitHub ↗

434msmeasured against a baseline, as published by the source
Use
Model and agent routing
Industry
Developer tools
Form
Open-source tool
Stage
Beta
Plugs into
ego lite
Listed
2026-09-26
Found via
discord
Repository
jiangkoumo/ego-decision-layer
Stars
31
Forks
2
Last push
2026-10-28
Language
JavaScript
License
MIT
ego-decision-layer screenshot
docs/demo.gif in the jiangkoumo/ego-decision-layer README, MIT; shown from GitHub.

The README opens with

给 ego lite 的可插拔决策层:默认 System One(Jev),可换本地 / 其他 OpenAI 兼容后端;执行层带 fail-closed 护栏。

当前能力:线性操作闭环、结构化抽取、动作缓存、批处理和 Canvas/SVG 图形区域兜底。 各能力都有对应测试,见功能验证;历史性能数据的条件与复跑脚本见测量与复跑基准。 CHANGELOG.md 保留修复记录和被实测推翻的旧结论,代码级溯源见 THIRD-PARTY.md。 最新版 v0.13.0:P2 真实双宿主基准扩至 8 项任务(包含 HN 4 类列表与 Wiki 多词条搜索),增加有界被动诊断与离线分析;修复目标缺失与滚动的交替循环及揭示配额重置边界,并隔离动态时钟干扰。首轮 16 次试验为 13 次达成、错误成功 0;复跑命令、原始记录与小样本限制见测量说明。发布页提供源码下载;不同安装方式的更新规则见下载与更新渠道。

English summary: ego-decision-layer replaces the per-step LLM round trip in browser automation with TypeSafe's System One model Jev. Jev reads one indexed element table and answers, in a single request, both the operation (click / typetext / select / scrollup / scrolldown / wait / done / blocked) and the target element. Code owns observation,...

Badge

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

Listed in Jev in production

Also used for model and agent routing