AI 智能体2 weeks ago
Mailpipe — The AI-native email platform
通过MCP、API和CLI连接AI代理的电子邮件平台。
@Mailpipe_dev · X
AI-native email with human oversight
完整作品展
技术栈
121 projects
通过MCP、API和CLI连接AI代理的电子邮件平台。
@Mailpipe_dev · X
AI-native email with human oversight
用AI智能体创建动画视频作品的创作平台
@JOKEONE6666 · X
最近帮 Web2 的团队做了一个 AI 精品漫剧，在优酷签了独家，感对 AI 制作又找到了新的感觉。全程在 完成制作，感觉体验起来还是很棒的，接下来准备开始尝试用纯 AI 做 Web3 的内容了 #Seedance #RunNOW
将 SEO 优化集成到 Claude Code 和其他 AI 编码代理中。
Sharanxxxx
用 AI 和人工代理在一个收件箱管理客户支持,可自托管或云端。
@ompharate · X
— an open-source, agentic alternative to Intercom and Zendesk.
通过 SalesTouch MCP 连接 Claude 和 LinkedIn 自动化销售任务。
@AntoineDsh · X
Hey I'm building a to run your LinkedIn outreach on autopilot with Claude. Let's connect !
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
粘贴URL生成llms.txt和MCP端点，使任何网站可被AI代理查询。
AshHackerNews · HN
AgentReady – MCP server that makes any docs site queryable by AI agents
用于在 git worktrees 中并行运行多个 AI coding agents 的桌面应用
vuphanse
用可视化编辑器构建和部署AI语音智能体，无需编码。
@mattcabral_ · X
looking for honest feedback from devs
比较AI模型在多个领域的基准评估成绩和排行榜。
davidtsong · HN
Benchmarklist: track AI benchmarks (2.4k+), models, and capabilities
通过 API 或 URL 替换将 X posts 转换为干净的 Markdown，供 LLMs 和 agents 使用
@larsbuilds · X
BotbaseAI：无需编码快速构建并部署 AI 客服机器人
@BotbaseAi · X
We just shipped 🚀 BotbaseAI — build & deploy an AI customer support agent in minutes. No code. Looking for early testers to break it and tell us what sucks. Try it → 🙏 RTs appreciated #buildinpublic #AI #SaaS