
如果你想要一个 AI「个人代理」,但又不想把自己的数据放在某个不透明的云端计算机上,现在有一个看起来更好的新选择:[rociiu] 推出了 talorys,这是一款运行在你 Cloudflare 账户中的 AI 代理。诚然,它仍然运行在云端计算机上,但那是属于你自己的账户。它的设计允许你在 Cloudflare 的免费账户上使用,并设有合理的限制,而且其运行代码全部托管在 GitHub 上,因此如果你愿意,可以查看它到底在做什么。此外,所有数据也都在你自己的云实例中。
这似乎是一个合理的折衷方案。Cloudflare 提供托管,而你的虚拟机中的软件负责完成所有工作。至少,宣传上是这么说的。老实说,我们还没有仔细审查过代码,但官方宣称「对免费用户友好……没有遥测」。
我们有相当高的把握认为他们也使用了 Cloudflare 的 AI 引擎,因此很好奇从理论上讲,他们在数据传输过程中能收集到多少你的数据。当然,你的数据仍然存储在云端,如果你真的担心隐私问题,这可能不适合你。但因为所有内容都在你的账户中且处于开放状态,你至少能对现有数据拥有更多控制权。例如,你可以轻松下载或删除你的数据。你甚至可以清楚地看到它使用了哪些提示词。
有哪些缺点吗?当然有。比如,该工具无法与你的日历集成。它无法处理电子邮件,也不能搜索网络。它不会为你编写代码。这并非旨在替代通用聊天机器人,而更像是一款用于维护待办事项列表的 AI 工具。
尽管 Cloudflare 提供免费套餐,但它设有每日额度,你可能会遇到上限。当然,如果类似功能过于流行,其限制可能会进一步收紧。不过,该系统确实支持你导出数据。
这并不完美。我们让它设置三个定期会议,结果只成功了一个,把另一个安排在周日而不是周一(尽管标题写着周一),还触发了 Cloudflare 的频率限制导致第三个会议创建失败。我们让它重试一次失败的会议,但没起作用。于是我等了一会儿再试,它声称成功了。然而当我查看日程时,那个会议并不存在。
然后我们让它修复周日的安排并重新添加漏掉的那个会议。这次它确实添加成功了。它还添加了周一的会议,但尽管它说会删除周日的会议,实际上并没有。我手动删除了它。
安装非常简单。你可以将自有域名连接到Cloudflare,或者使用pages.dev提供的子域名,两种方式都可以正常使用。只需在电脑上运行一条命令,它会自动处理服务器认证,并配置所有服务和数据存储。
所以本质上它是一个待办事项、提醒和笔记系统。但它一旦运行起来效果确实不错。它可以记住内容,并且能够非常容易地检索到它记忆中的信息或笔记中的内容。用非AI工具能做到吗?当然可以。更不用说了,任何一款主流聊天机器人都能做到所有这些功能以及更多。但它们无法在你的自有托管服务器上运行。
此外,有趣的是,对于小型用途,Cloudflare 提供大量的免费层计算资源,可能在其他项目中派上用场。拥有免费的云端计算机是件好事,正如我们在近期一篇 Linux Fu 文章中提到的,当时我们使用了 Oracle 的免费服务器。
本文来源:https://hackaday.com/2026/10/12/a-free-cloud-ai/
若有版权问题,请来信告知:13951431913#139.com 或在右方提交评论。
This seems like a reasonable compromise. Cloudflare provides the hosting, and the software in your virtual computer does all the work. At least, that’s how it is promoted. Honestly, we haven’t combed over the code, but the assertion is “Free-tier friendly… no telemetry.”
We are fairly sure they are using Cloudflare’s AI engines, too, so it would be interesting to see how much of your data they could, in theory, harvest in transit. Of course, your data is still in the cloud, so if you are really worried about privacy, this might not be for you. But since everything is in your account and open, you can at least have more control over what’s there. For example, you can easily download or delete your data. You can even see exactly what prompts it uses.
Are there downsides? Sure. The tool can’t integrate with your calendar, for example. It can’t deal with e-mail, nor can it search the web. It won’t write code for you. This isn’t meant to be a general-purpose chatbot replacement. It is more like an AI tool for keeping a task list.
While Cloudflare does have a free tier, it does have daily limits, and you may hit them. And, of course, if things like this get too popular, they could reduce those limits. The system does let you export your data, though.
It isn’t flawless. We asked it to set up three recurring meetings. It got one right, put the other one in for Sunday instead of Monday (even though the title said Monday), and hit a Cloudflare rate limit and failed to create the third one. We asked it to retry the failed one once, and it didn’t work. So I waited a bit and tried again. It claimed it worked. However, when I looked at the schedule, it wasn’t there.

We then asked it to fix the Sunday schedule and add the one it had missed again. It did add it that time. It also added the Monday meeting, but despite saying it would delete the Sunday one, it didn’t. I manually deleted it.
Installation is easy. You can connect a domain you own to Cloudflare or use the subdomain on pages.dev that they give you, which works fine. You run a single command on your computer. It handles authentication to the server and sets up all the services and data stores.
So essentially it is a to-do, reminder, and note-taking system. However, it does work well when it works. It can remember things and will find things it remembers or in notes very easily. Can you do that with non-AI tools? Of course. Not to mention, any of the “big” chatbots can do all of that and more. But not in your own hosted server account.
Besides, it is interesting that for small uses, Cloudflare offers plenty of free-tier compute resources that might come in handy for other projects. It is nice to have some free cloud-based computers, as we noted in a recent Linux Fu post where we used Oracle’s free servers.