我为代理创建了一种安全的方式，可以通过 HyperDHT 向您请求密钥。
2 分•作者: smashah•大约 1 个月前
大家好，
我有点厌倦了不得不将秘密信息交给我的代理，以及在整个流程中（包括 Harness、模型路由器、模型提供商、训练集、聊天应用程序等等）可能出现的潜在泄露风险。因此，我决定创建 peardrop.fyi——这个工具允许你的代理声明式地生成秘密请求页面/链接，你可以通过 Web 或 CLI 来填写。代理可以确定一个脚本，在接收到值后运行，或者将这些值放入目标文件夹。如果你想将某些内容放入你的机器保险箱/钥匙链，而又不想让代理访问凭据或浏览器，这将非常有用。
这是仓库地址：https://github.com/smashah/peardrop
（CLI、核心和可自托管的中继都是开源的）
查看原文
Hi all,<p>I kinda got sick of having to give secrets to my agents and all the potential leakage in the pipeline (with the harness, the model router, the model provider, the training set, the chat application etc etc) so I decided to make peardrop.fyi - this tool allows your agent to declaratively generate secret request pages/links which you can fill in via web or CLI. The agent can determine a script that runs once the values are received or can put them in a target folder. This is useful if you want to put something in your machine vault/keychain without either giving access to the credentials or the browser to the agent.<p>here is the repo: https://github.com/smashah/peardrop<p>(cli, core and self-hostable relay are all open source)