Offload: Fully private AI for any website using local models.
工具 / Tools
A fully private in-browser AI assistant. Works even offline. No external API dependencies.
用户数
32
评分
5.0
评论数
3
7 天增长
-3|-8.57%
信号待补齐未识别到付费功能高风险权限组合
Local LLM
Use Local LLM extension: run llm locally (LLama 70B or DeepSeek with WebLLM + Gemini Nano), ask ai models on your tabs - private ai.
用户数349当前公开安装规模
评分4.4商店平均评分
评论数9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
3 项素材Local LLM 媒体预览
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。
7 日评分变化
起始值
4.44
最新值
4.44
7 日评分变化
--
2026年7月10日2026年7月10日
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日增长减少
-3-0.82%7日增长暂无数据
----30日增长减少
-36-9%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1.12.0
ManifestV3
大小7.67MiB
语言数52Deutsch / English / Filipino +49
发布时间
最近更新
最近抓取
DeutschEnglishFilipinoIndonesiaKiswahiliMelayuNederlandsTiếng ViệtTürkçecatalàdanskeesti
简介
插件简介
查看插件说明、主要功能和适用场景。
Meet a browser helper that makes running local models feel natural, fast, and private. If you like theese chats and want to have your personal, which will run on your computer - that's it. You now not limited for external services and can download it.
Chat about website, pdf or any other file just in your browser. Get a good summary of pages. It is built for people who want a smooth and clean local llm ui, and a practical way to ask assistant while browsing.
🚀 Next models available for local usage:
- Google’s Gemini Nano - embedded in Chrome
- DeepSeek R1 Distill Llama 8B - deep thinking - running on your local
- Gemma 2 2B
评价
最新评论快照
查看最近评论和评分分布。
商店综合星级4.4Chrome 商店给出的聚合评分，包含只有打分但没有同步评论正文的情况
已同步评论均分4.3仅基于下方已同步评论正文计算
有内容评论7已同步的评论正文数量
总评分/评论数9Chrome 商店公开评分/评论计数
商店综合星级：4.4。下方星级分布只统计已同步评论正文；如果某个插件只有公开分数、没有真实评论正文，这里可能为空。
相关推荐
同类与相关插件
查看 Chrome 商店详情页中的相关产品。
DeepSeek AI
工具 / Tools
免费增值置信度 64
Use DeepSeek AI – smart instant AI-powered conversations with DeepSeek. Chat seamlessly and boost productivity with Deepseek!
用户数
9K
评分
4.2
评论数
30
7 天增长
0|0%
Local LLM Helper
工具 / Tools
Interact with your local LLM server directly from your browser.
用户数
274
评分
1.8
评论数
5
7 天增长
--|--
SideAll: Chat Sidebar - GPT, Claude, DeepSeek
工具 / Tools
Access your favorite AI chat websites in one sidebar — side-by-side with your work. No tab switching needed.
用户数
9K
评分
4.8
评论数
152
7 天增长
0|0%
AnythingLLM Browser Companion
工具 / Tools
Bring AnythingLLM directly into your browser to curate and collect content on the web directly into your AnythingLLM workspaces.
用户数
10K
评分
4.4
评论数
12
7 天增长
0|0%
Offline GPT: Offline (local) AI Chat Assistant
工具 / Tools
Chat with AI using locally downloaded models (WebLLM) and current page context
用户数
115
评分
5.0
评论数
2
7 天增长
-10|-6.9%
Hey tell me which model is the fastest in this like blazing fast also i am on a gaming pc with 6GB RTX 3050
Useful, but the "private" claim is incomplete, and the rating widget is **deceptive**. The store description says "no query will leave your computer." That part is true, prompts and page content stay local. Local inference works as advertised. The 5-star widget in the sidebar is the part to flag. - Clicking 1, 2, or 3 stars sends your feedback to a private Google Form only the developer sees. - Clicking 4 or 5 stars sends you to the public Web Store review page. The UI gives no hint of the difference. This is how the public rating stays high while critical feedback never reaches other users. The extension also sends anonymous usage telemetry to Google Analytics on every interaction: - Every sidebar open - Every model selected, loaded, or used (with model ID and timing) - Every message sent, page attached, chat cleared, or generation cancelled - Every model download — started, succeeded, failed, or abandoned (including how far you got before cancelling) A persistent random ID is stored locally and sent with every event, so all activity from one install is linkable across sessions. No prompt or page content is included, only the metadata above. There is no opt-out toggle. Disabling telemetry requires editing the source code. Other things worth knowing: - Model weights download from a CloudFront bucket the developer controls, not the official MLC-AI distribution. - The extension can read and inject scripts into every page you visit. The local inference works. The privacy framing and the review-funneling do not match what's described on the store page.
Довольно удобное расширение, спасибо разработчикам!
this is a really cool browser extension, super handy. simple way to run llm, i use it pretty much every day.
Works surprisingly well offline.
Great extension, fast and accurate results!
Finally someone made this tool. Been looking for it for a long time