
Mushroom Identifier - Fast & Accurate Mushroom Identification
AI蘑菇识别工具,快速准确,包含毒性检查和危险相似种警告。
Mushroom Identification — 蘑菇 AI 识别工具(快速、准确),结果包含毒性、高危相似种警告
完整作品展
技术栈
60 projects

AI蘑菇识别工具,快速准确,包含毒性检查和危险相似种警告。
Mushroom Identification — 蘑菇 AI 识别工具(快速、准确),结果包含毒性、高危相似种警告

搜索餐厅,发现当地人真正吃饭的地方,避免旅游陷阱。
kingchesco · HN
I know $90 for a dining app sounds absurd. And it’s not even an app; it's a wrapper for an LLM. But it is how it is built that makes it so expensive. I had to make a whole API just to call it (which because its own SAAS). All just to bypass dumb google reviews. Google Maps and reviews send people to places optimized for tourists and good copywriters. To find actual local hole-in-the-walls algorithmically, I had to first build that api (called BWENDI), a "spatial gravity" engine using 100GB+ of tweaked OSM, GeoNames, and other proprietary data. Instead of aggregating reviews, it mathematically calculates foot-traffic, throughput, transaction stats, and economic criticality among other factors. Bwendi is A Python/Node ETL pipeline feeding an LMDB-backed context API. It uses a proprietary 1MB binary grid served via Cloudflare Workers for millisecond edge reads with near-zero overhead, hosted in Switzerland. This was done of course to get the purest location context around every street

Tako 在 60 秒内扫描网页应用,发现泄露密钥和开放数据库等安全漏洞。
@guhanvenkaty · X
Tako's free preview is live: Paste your URL, get a security verdict on your vibe-coded app in 60s. Not an AI wrapper: it fires real requests and PROVES exposure, pulling data from your open DB with no login. Scanning puts you on the early-access waitlist.

裁剪、编辑、模糊和导出截图,完全私密,无需上传任何数据。
@noshkass · X
Built SAFEFRAME a private, browser-only screenshot sanitizer. Crop, blackout, blur, and export sensitive screenshots without uploading a single byte. Try it: Built with ChatGPT Sites. @chatgptapp #Giveaway

在 Free Market 上浏览、购买和出售农产品及手工商品。
@JoshuaHenr3593 · X
Just launched: Free Market (FMK) 🛒 A free marketplace for sellers, artisans & delivery riders — inventory tools, sales tracking, and profiles, no fees. Check it out 👉 RTs appreciated 🙏 #FreeMarket #FMK #buildinpublic

分析文本以识别 10 种有毒和 7 种健康的沟通模式。
@WEreFrame · X
Underrated...well I wouldn't say that because I'm just starting, but overlooked maybe. The impact on humanity will be noticed across the globe. Stop reacting. Start reFraming.

为餐饮企业生成精美在线菜单和AI营销内容。
@Lsdavo · X
built in 2 days with claude code. the unlock: gave it our design system first - colors, type, components. after that every iteration stayed on-brand automatically. no mockups. no handoffs. describe → review → refine.

按下 Nothing Button,看看会发生什么。
@saralsachan · X
Waste you time on weird websites

追踪 Pump.fun 代币,识别恶意钱包地址和地毯拉动风险。
@ha_li60704 · X
他的技术力量确实很强 解决了很多我想解决而没解决的问题 大家可以试试网站: 查询速度非常快,而且可用信息占比极高 可以说已经是成熟的打狗神器了 我分析了他的数据源,他自己做了一个庞大的数据库,有一个订阅源 这不是开玩笑的东西,这是真技术,很久没见过的真东西 J5ZognFJEepsWsCQPmqVchvEvsUMomEkxd8LbMrH2J7

发现 cannabis 食谱、strain 档案和个性化 wellness 推荐
@saidzaripov · X

一个作为Roblox替代品的FPS游戏。
davitb · HN
I'm a father of two, 7 and 12. They are obsessed with Roblox, especially Rivals. Like a lot of parents, we did not love it. We tried the usual things: block it, limit it, set timers." It became a daily battle, a lose-lose situation. So I flipped the problem. Instead of fighting what they loved, I decided to lean into it, but with a twist. Why just play an FPS when you could build one together? My kids became the PMs. Claude and I became their engineer. I was shocked by how fast we moved. We picked a name, Cooked and started building. Get in. Lock in. Get cooked! In the first 3 hours, we had an actual FPS we could play together in the browser. Next day I invited my friend's two kids over. Suddenly, I had four PMs. We had 3 laptops, 1 iPad and 1 iPhone. So in 30mins we added mobile support and could play all 5 together. The kids would ask for features: "Can we have a rocket launcher that knocks people off the map?" "The knife should stab faster when you hold it." I know al

连接钱包分析链上持仓风险,发现交易机会
@daweifs · X
最近我用 @dappOS_com 的 AI Coding 做了一个交易助手,整个过程大概十分钟。实际体验完以后,我发现它能做的并不只是交易工具,AI 伴侣这类产品同样可以快速落地。 先放一下我做的成品,连钱包就能体验: 🔗 币圈本来就不缺工具。 看持仓、查聪明钱、盯新池子、看流动性,每一项都有专业平台。但我自己用下来,最麻烦的从来不是找不到数据,而是数据散在不同地方。 平时判断一个币要不要继续拿,我得先看仓位占比,再查流动性、大户地址和近期资金异动。 想找新机会,又要换到新池子监控、安全检测和交易路径工具。 开了一堆页面,最后还是要自己把信息重新拼一遍。 所以这次我没有继续找一个功能更多的平台,而是把自己的交易习惯直接告诉 dappOS AI Coding: 帮我做一个能连接钱包,同时完成持仓风险检查和新机会筛选的交易助手。 十分钟左右,一个能直接使用的网站就生成出来了。 目前我觉得比较实用的是两个功能。 第一个是持仓风险检查 连接钱包后,它会把资产集中度、近期活动、代币流动性和大户变化放在同一个页面里。 和普通钱包看板相比,它不只是告诉我持有什么,而是让我先判断: 哪个仓位占比过高; 哪些资产的流动性需要注意; 哪个币近期出现了异常变化; 今天最应该先检查哪个仓位。 以前这些信息要分散到几个平台查看,现在可以先在一个页面里完成初筛。 第二个是新机会筛选 很多新币扫描器的问题不是没有信息,而是信息太多。 一天几十上百个新池子、资金异动和聪明钱提醒,真正值得继续研究的可能只有几个。推送看多了,反而容易被情绪带着走。 我做的这个工具会根据流动性、锁仓情况、资金变化和风险信息,先把候选项目整理出来。 它不会替我决定买什么,也不会承诺收益,但能过滤掉一部分噪音,让我把注意力放在少数值得继续研究的目标上。 对我来说,dappOS AI Coding 和普通交易工具最大的区别,不是多了一个风险评分,也不是数据一定比专业平台更多。 而是我可以让产品按照自己的交易流程工作。 普通工具的页面、指标和操作路径都是固定的,用户只能慢慢适应;使用 AI Coding,我可以直接告诉它自己先看什么、后看什么、哪些数据需要放在一起,以及最终希望解决什么问题。 工具开始适应人,而不是人去适应工具。 这可能也是现在 OKX 推进 https://t.