生产力2 weeks ago
PDF Reflow
使用本地AI模型在浏览器中重排PDF。
ldenoue · HN
Show HN: PDF reflow in the browser with local AI model
完整作品展
技术栈
60 projects
使用本地AI模型在浏览器中重排PDF。
ldenoue · HN
Show HN: PDF reflow in the browser with local AI model
上传视频素材，获取优化观众留存的AI编辑版本
@QuiseBuilds · X
- drop raw footage. Atlas maximizes retention. No editing needed.
上传产品图片，选择场景，AI生成专业级摄影照片。
@aftertakenai · X
for AI e-commerce product photography
在浏览器中本地批量调整、裁剪、压缩和转换图像。
@MaximMitenkov · X
🔒 Just launched Image Pipeline — batch image processing in your browser. 100% private. No signup. Pay once, use forever. #buildinpublic #webdev #privacy
AI视频编辑器，自动剪辑、添加图形动画、应用主题生成成品。
pireel · GitHub
pireel Open-source, backend-free AI video editor for talking-head video — storyboarding, designed graphics, kinetic captions, themes and in-browser WebCodecs export. Drivable by any AI agent over MCP.
检测并替换图像中的文本，同时保留布局和样式。
PicText - 图片文字编辑器 — AI 驱动的图片文本编辑器，检测并替换照片、截图和产品图中的文本，同时保留原始布局和字体
将您的音频或文本脚本转换为Avatar Clip定制视频。
@CyberBlueCollar · X
Faceless content booster 🚀
拖拽图像进行拼图、九宫格切割或AI分割，本地处理无需上传。
@lanford87746071 · X
上线了一个小工具：羊咩像素 WoollyPix 🐑 在线拼图 / 九宫格切图 / AI 智能分割 / 截图美化 全程本地处理，不上传图片，免费无广告
用AI从长视频自动生成短视频片段并导出为社交媒体格式。
@tryFrameOS · X
在浏览器中为视频生成多种风格的动画字幕，无需上传，完全隐私。
@Rajveer_k12 · X
we just shipped 🚀 Kaption AI is live & free — upload a video, get captions in multiple styles. 100% in your browser, no data leaving your device. built with @aayaan_07 → feedback appreciated 👇 #buildinpublic
捕获UI元素及其代码上下文，与AI代理分享以调试视觉缺陷。
Loerei · HN
I found that describing where a broken UI is and taking screenshots for AI agents really sucks. I’m too lazy to explain an indescribable visual bug or capture a millisecond-long flash. I also don’t want to remember which file defines an element, whether it's right in the .tsx or a problem with the Parent Styles in .css. And even if you can point out the exact file, your agent still has to dig through thousands of lines of code to know what on earth you're yapping about. In a 7700-file monorepo like Cal.com, simply giving the right file in the prompt for your agent saves about 68.9% of execution time and 94.2% of the tokens your agent needs to digest. HoverSource gives all the needed information and further pushes it to -88.5% time and -94.5% tokens, basically skipping the entire digging session and jumping straight to reasoning and executing. The save is linear to how big your codebase is. I want to save tokens, but don’t want to spend my time and energy digging manually, and a junio
