
Mindola | Your Digital Twin for AI Intake
用你的知识创建AI数字分身,用你的声音回答访客问题。
@withmindola · X
let's go! you can build you digital twin by feeding all your content and share it with people so they can talk to your second brain in your own voice.
完整作品展
技术栈
60 projects

用你的知识创建AI数字分身,用你的声音回答访客问题。
@withmindola · X
let's go! you can build you digital twin by feeding all your content and share it with people so they can talk to your second brain in your own voice.

通过一个 API 密钥统一访问 OpenAI、Claude、Gemini 等 200+ AI 模型。
TaylorM492 · HN
InferAll – One API for OpenAI, Anthropic, Google, Nvidia Nim

使用 Claude Code 构建可通过 SMS 与外部系统交互的 AI agent。
jacobgc · HN
Outside Agent – Build SMS Agents from Claude Code


从URL或描述生成SaaS启动视频,60秒内完成AI优化编辑。
@VanillaSkyAI · X
is like Lovable for video. Paste a URL, get a launch video, chat to edit, post 🎬 Here's one I made in minutes 👇

让AI模型通过3D动画展现香蕉植物的完整生命周期来比较性能。
fran-mora · HN
I gave 5 AI coding agents one prompt: grow a banana plant through its whole life in three.js: sprout, leaves, flower, fruit, rot, then pups that restart the loop. It's deceptively simple and yet very hard to get right from procedural code: you have to write working three.js and understand how the plant is actually built; how it hangs, ages and decays. Get the biology wrong and the code renders something weird. These are agents, not bare models (Claude Code and Codex for now). They can use tools, including playwright to check their work and improve it.

追踪 AI 行业关键变化与证据支持的趋势。
barretlee · GitHub
agent-pulse Evidence-backed AI industry intelligence — trends, source updates, daily data refreshes, and weekly decision briefs.

ARGUS:为AI代理流程的可观测性平台,检测故障并解释根本原因。
@VaraadDurgaay · X
Solving the prb of observability in ai agents

一次存储共享记忆,在AI系统和团队中复用。
Repeater22746 · HN
ContextVault – Shared memory layer for your AI and your team

监控AI API中转站并访问精选网关推荐。
yaojingang · GitHub
TokHub AI API 中转站监控、推荐运营与 OpenAI 兼容专属网关系统,支持分层探测、健康评分、用量计量、告警审计和 Docker 自托管。

在AI助手间共享上下文,让它们记住代码库和任务历史。
@dorikuio · X
AI agents have amnesia — Claude Code figures out the codebase, an hour later Codex starts from zero. So I built a shared memory + task board for every MCP agent — Claude Code, Codex, Cursor, Gemini CLI: Is this just my problem? Help me find out.

一个共享记忆层,在不同的 AI 工具和设备间保留你的决定、偏好和项目。
upload — 跨 AI 的长期记忆层,让 ChatGPT、Claude、Codex、Hermes、OpenClaw、WorkBuddy 等共用同一份记忆,换工具换设备都接着上次继续,注册即用免装插件