信号待补齐未识别中风险权限组合

lfl-terminal

Browser terminal with deterministic commands and a local LLM that proposes page actions you approve. Nothing leaves your machine.

用户数0当前公开安装规模

评分--商店平均评分

评论数0公开评论体量

Manifest 版本V3插件平台版本

7日增长--近 7 天净增用户

7日增长率--相对周增长速度

视觉预览

lfl-terminal 媒体预览

4 项素材

趋势

用户增长趋势

按已采集快照查看用户数变化。

用户增长趋势

评分趋势

近 7 日评分趋势

展示最近 7 日窗口内已采集的评分快照，辅助判断近期评分是否稳定。

评分趋势样本还不够，后续快照会继续补齐。

增长概览

日/周/月增长表现

同口径展示 1 天、7 天、30 天的绝对增长与增长率。

1日增长暂无数据

----

7日增长暂无数据

----

30日增长暂无数据

----

技术摘要

版本、语言与抓取信息

查看发布时间、版本、支持语言、最近更新和抓取时间。

版本0.4.0

ManifestV3

大小122KiB

语言数1English (United States)

发布时间--

插件简介

查看插件说明、主要功能和适用场景。

lfl-terminal is a keyboard-first terminal that lives in your browser. Press the backtick key on any page and a terminal overlay slides up. Type deterministic commands to read, search, navigate, and act on the page. For anything that needs interpretation, a local AI model (one you run yourself) proposes a single action that you approve or reject before it ever touches the page.

The whole point is local-first, human-supervised control:

- Nothing leaves your machine. Deterministic commands run entirely in your browser. The AI half talks only to a local model on your own computer (loopback, 127.0.0.1). There are no accounts, no servers, no telemetry.

- The model proposes; you decide. Any action that changes the page (click, fill, navigate) is shown to you as a plain, deterministic summary and waits for your explicit approval. Read-only commands run without a gate.

- The model is never a security boundary. Approval, the fixed set of allowed actions, and the hard blocks (for example, credential fields are never auto-filled) are enforced by the extension's own code, not by the model.

What you can do:

评价