
FileChangeCategorizer is a lightweight Chrome extension that adds automatic file categorization to GitHub commit histories and pull request diffs. You define the rules once, and every changed file gets grouped and labelled the moment you open a pull request, so large diffs stop looking like an undifferentiated wall of paths.
| 面向/指標 | ![]() | |
|---|---|---|
| 官方網域 | deepseek.com | chromewebstore.google.com |
| 定價模式 | 免費增值 | 免費 |
| 每月造訪次數 | 3.73億 (372,761,591) | 0 (0) |
| 月流量變化量 | +1536.22萬 (+4.3%) | 0 (—) |
| 主要市場與市佔 | 🇨🇳 中國 (50.5%) | 🌐 全球 (—) |
| 每月直接造訪 | 2.92億 | 0 |
| 使用者評分 | 4.8 | 3.9 |
| 支援平台 | 網站 | 瀏覽器擴充功能 |
由 DeepSeek-V4 與 R1 驅動的高效開源權重與託管推理 AI,token 成本極低。
依託稀疏混合專家架構(V4-Pro 為 1.6T 中的 49B 啟用參數),以極低延遲與記憶體開銷處理最多 100 萬 token。
由 DeepSeek-R1 開創並融入 V3.2 與 V4 思考模式,對複雜數學、邏輯與程式碼除錯展示逐步自驗證過程。
快取命中時,輸入 token 成本降至 Flash 的每百萬 0.003 美元與 V4-Pro 的每百萬 0.022 美元,離峰 UTC 時段費率再低 50%。
在 chat.deepseek.com 及 iOS/Android 上免費提供文件上傳、推理模式與網頁搜尋,核心模型無須付費牆。

FileChangeCategorizer is a lightweight Chrome extension that adds automatic file categorization to GitHub commit histories and pull request diffs. You define the rules once, and every changed file gets grouped and labelled the moment you open a pull request, so large diffs stop looking like an undifferentiated wall of paths.
Define your own matching rules and let the extension sort changed files in commits and pull requests into labelled groups automatically.
The categorization is applied inside the GitHub commit and pull request views you already use, with no dashboard to switch to.
Nothing is committed to your codebase and no CI setup is required, because everything runs in the browser extension.
Groups of related files make sprawling diffs easier to scan and review in a logical order.

提供巨大的上下文視窗與深度的 Google 生態系整合,但對於純推理任務感覺較不夠專精。
提供巨大的上下文視窗與深度的 Google 生態系整合,但對於純推理任務感覺較不夠專精。

免費 / 開源提供同等級的開源權重基礎模型與多語言效能,但需要自行架構主機或第三方推論設定。
免費 / 開源Enables running open-source models locally on consumer hardware, but lacks DeepSeek's cloud-scale hosted reasoning power.
免費 / 開源Enables running open-source models locally on consumer hardware, but lacks DeepSeek's cloud-scale hosted reasoning power.