# yeahhe365/Gemini-Nexus

Gemini Nexus 是一款面向浏览器场景的 AI 助手扩展，集成 Gemini Web、Gemini API 与 OpenAI 兼容接口，支持网页上下文、图像处理、工具调用和 MCP 浏览器控制。

Repository: https://github.com/yeahhe365/Gemini-Nexus
Canonical: https://ross.abutalabs.com/products/gemini-nexus
Language: JavaScript
License: MIT
License Family: permissive
Topics: browser-automation, chrome-extension, gemini, google-gemini, llm, manifest-v3, side-panel
Last push: 2026-08-25T10:59:40+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 18
- inputs: {"age_days": 257, "days_push": 8, "days_rel": 9, "gap_med": 1.0, "n_releases_24m": 23}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1088, forks 150 (observed 2026-08-28T04:03:32.434246+00:00)

## What it is
Gemini Nexus is a Chrome extension (Manifest V3) that adds an AI assistant layer to the browser, integrating Gemini Web, the Gemini API, and OpenAI-compatible endpoints. It supports page context, image and screenshot input, tool calling, CDP-based browser control, and external MCP tools.

## Use cases
- chat with an AI assistant about the current web page
- use Gemini in the browser without an API key
- let an LLM control the browser via MCP tools
- analyze screenshots and images with AI in a side panel
- connect OpenAI-compatible APIs to a browser assistant
- automate browser tasks with AI tool calling

## When to choose
- you want a browser-native AI assistant with page context
- you need MCP or tool-calling support inside Chrome
- you want one extension supporting Gemini Web, Gemini API, and OpenAI-compatible providers

## When to avoid
- you need a fully ToS-compliant Gemini integration (Gemini Web access reverse-engineers internal endpoints)
- you are uncomfortable with watermark removal from generated images
- you need a Firefox or non-Chromium browser extension

## Facets
- artifact type: plugin
- maturity: active
- function: chatbot, llm-inference, mcp, browser-extension, image-processing, agent-framework
- domain: browser-extensions, artificial-intelligence, large-language-models
- platform: browser-extension, browser
- tags: gemini, chrome-extension, manifest-v3, side-panel, openai-compatible, browser-automation, web-context, screenshot-input, ai-agents, automation

## Member repositories
- yeahhe365/Gemini-Nexus (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:32.434246+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:49:24.059977+00:00, confidence not recorded.
  - readme: https://github.com/yeahhe365/Gemini-Nexus (fetched 2026-08-28T04:03:32.434246+00:00, sha 4690acb35783)
- Data as of 2026-08-30T08:39:29.467469+00:00.