HackerNews中文版

我一直在构建AI代理工具，并不断遇到同一个问题：代理浏览网页、执行操作、填写表单、抓取数据——但对于实际发生了什么却没有任何证据。截图可以伪造，日志可以被编辑。如果出现问题，你只能对着一个黑箱指指点点。因此，我构建了Conduit。它是一个无头浏览器（底层使用Playwright），能够将每个操作记录到一个SHA-256哈希链中，并用Ed25519对结果进行签名。每个操作都会与之前的哈希进行哈希运算，从而形成一个防篡改的链。在会话结束时，你将获得一个“证明包”——一个包含完整操作日志、哈希链、签名和公钥的JSON文件。任何人都可以独立验证这个包，而无需信任生成它的方。我主要针对的使用案例包括： - *AI代理审计*——你给代理一个浏览器。稍后你需要证明它做了什么。Conduit为你提供加密凭证。 - *合规自动化*——SOC 2、GDPR数据主体访问工作流程，任何需要证据表明某个过程正确运行的场景。 - *网页抓取来源证明*——证明你收集的数据确实来自你所说的地方，并且是在你所说的时间。 - *诉讼支持*——以可验证的保管链捕获网页内容。它还作为一个MCP（模型上下文协议）服务器发布，因此Claude、GPT和其他基于LLM的代理可以通过工具调用原生使用这个浏览器。代理可以进行浏览、点击、填写、截图，而证明包会在后台自动生成。免费，MIT许可证，纯Python。无需账户，无需API密钥，无需遥测。 GitHub: https://github.com/bkauto3/Conduit 安装：`pip install conduit-browser` 欢迎对证明包格式和MCP集成提供反馈。很高兴回答有关加密设计的问题。

查看原文

I've been building AI agent tooling and kept running into the same problem: agents browse the web, take actions, fill out forms, scrape data -- and there's zero proof of what actually happened. Screenshots can be faked. Logs can be edited. If something goes wrong, you're left pointing fingers at a black box.So I built Conduit. It's a headless browser (Playwright under the hood) that records every action into a SHA-256 hash chain and signs the result with Ed25519. Each action gets hashed with the previous hash, forming a tamper-evident chain. At the end of a session, you get a "proof bundle" -- a JSON file containing the full action log, the hash chain, the signature, and the public key. Anyone can independently verify the bundle without trusting the party that produced it.The main use cases I'm targeting:- *AI agent auditing* -- You hand an agent a browser. Later you need to prove what it did. Conduit gives you cryptographic receipts. - *Compliance automation* -- SOC 2, GDPR data subject access workflows, anything where you need evidence that a process ran correctly. - *Web scraping provenance* -- Prove that the data you collected actually came from where you say it did, at the time you say it did. - *Litigation support* -- Capture web content with a verifiable chain of custody.It also ships as an MCP (Model Context Protocol) server, so Claude, GPT, and other LLM-based agents can use the browser natively through tool calls. The agent gets browse, click, fill, screenshot, and the proof bundle builds itself in the background.Free, MIT-licensed, pure Python. No accounts, no API keys, no telemetry.GitHub: https://github.com/bkauto3/ConduitInstall: `pip install conduit-browser`Would love feedback on the proof bundle format and the MCP integration. Happy to answer questions about the cryptographic design.

展示HN：Conduit——带有SHA-256哈希链的无头浏览器 - Ed25519审计轨迹